Mooncake Files

What's Changed

• docs: reflect WITH_NVIDIA_PEERMEM change from CMake flag to runtime env var by @stmatengss with @Copilot in https://github.com/kvcache-ai/Mooncake/pull/2164
• feat(rdma): mlx5dv QP path diversity via UDP sport and LAG port balance by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/2175
• [TENT] Enhanced QoS and Slice Spraying for TENT by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2048
• [TENT] Add codeowner to the TENT directory by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2183
• Add release-npu workflow by @JieTang66 in https://github.com/kvcache-ai/Mooncake/pull/2178
• [chore] Set default for WITH_NVIDIA_PEERMEM to true by @ShangmingCai in https://github.com/kvcache-ai/Mooncake/pull/2192
• [Store] Add structured object store helper by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2140
• Bump version to 0.3.11.post1 in pyproject.toml by @ShangmingCai in https://github.com/kvcache-ai/Mooncake/pull/2194
• [build] Strip shared libraries to reduce NPU wheel size by @JieTang66 in https://github.com/kvcache-ai/Mooncake/pull/2202
• [Docs] Update README with citation details by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/2190
• [Doc]: Update vLLM LMCache guide for MP interface by @fcczzz in https://github.com/kvcache-ai/Mooncake/pull/2209
• [Store] fix gauge overflow by separating DFS unlimited flag by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/2152
• [Store]: avoid INVALID_REPLICA error on empty offload by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/2151
• [Store] Fix: Auto-recovery for SSD Offload after Master Restart by @Colors-111 in https://github.com/kvcache-ai/Mooncake/pull/2077
• [Store] Fix: validate HA backend availability during config parsing by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2111
• [Doc] Add missing aws-logo by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/2211
• [codex] Update snapshot object store docs by @Dao007forever in https://github.com/kvcache-ai/Mooncake/pull/2148
• [TE] Python api "register_memory" & "batch_register_memory" support location param by @A-Liuhao in https://github.com/kvcache-ai/Mooncake/pull/2191
• [Bugfix][Store] Fix snapshot failure when OpLog has never been written by @leonzzhu in https://github.com/kvcache-ai/Mooncake/pull/2144
• [Build] Fix compile warnings across multiple components by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2193
• [Store] fix batch tensor allocation error code by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2226
• Fix MACA nvlink allocator build by mapping CUmemAllocationHandleType by @muma378 in https://github.com/kvcache-ai/Mooncake/pull/2227
• [Docs]: fix docs config, remove autodoc2, archive zh docs, add .agents/… by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2218
• [TransferEngine][MACA] Add missing CUDA-like type aliases for MACA compatibility by @Dayuxiaoshui in https://github.com/kvcache-ai/Mooncake/pull/2230
• [TENT] Add rule-based transport and device selection by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2079
• [TE] Add ProgressWorker skeleton by @ZhenyuePan in https://github.com/kvcache-ai/Mooncake/pull/2199
• [Store] remove invalid kMaxSliceSize assertion in AllocateBatch by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/2165
• [CI] Add docs-check job to validate Sphinx build with -W by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2229
• [Store] Add opt-in grouped object routing semantics by @CAICAIIs in https://github.com/kvcache-ai/Mooncake/pull/2180
• feat(store): add SPDK NoF worker pool by @Enigmo-x in https://github.com/kvcache-ai/Mooncake/pull/2172
• [Store] (CI run_tests_with_ssd failed / promotion-on-hit failed) eliminate race conditions by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/2235
• [TransferEngine][docs] document FI_EFA_USE_DEVICE_RDMA=0 for same-host EFA loopback by @Chelseatr in https://github.com/kvcache-ai/Mooncake/pull/2222
• [Doc] update overall picture by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2249
• [CI] feat: pre-release ci workflow by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2212
• [Doc] Clarify TENT failover poll behavior by @ZhenyuePan in https://github.com/kvcache-ai/Mooncake/pull/2208
• [Security] Fix Go vulnerabilities in libetcd_wrapper.so by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2250
• Build tent by @Dao007forever in https://github.com/kvcache-ai/Mooncake/pull/2089
• [Store] Clarify cache stats semantics by @CAICAIIs in https://github.com/kvcache-ai/Mooncake/pull/2248
• feat(store): route NoF replicas through put and get by @Enigmo-x in https://github.com/kvcache-ai/Mooncake/pull/2247
• [Doc] Split LMCache vLLM MP and non-MP guides by @fcczzz in https://github.com/kvcache-ai/Mooncake/pull/2268
• [PG][EP] Fix engine.so runtime dependency by @mmangkad in https://github.com/kvcache-ai/Mooncake/pull/2255
• [Store] Implement tenant metadata map isolation by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2232
• [EFA] Add MC_EFA_CQ_THREADS env var to cap CQ poller threads by @yuhuiaws in https://github.com/kvcache-ai/Mooncake/pull/2113
• [TransferEngine][ROCm] Add HIP dmabuf MR registration for AMD GPUs (fixes [#751]) by @andyluo7 in https://github.com/kvcache-ai/Mooncake/pull/2225
• [Store] enables the Ubtransport for Mooncake Store And optimize UrmaEndpoint by @zchuango in https://github.com/kvcache-ai/Mooncake/pull/2196
• [Store] L2->L1 promotion-on-hit: observability metrics + max_per_heartbeat knob by @yzhan1 in https://github.com/kvcache-ai/Mooncake/pull/2176
• fix(metrics): show actual client-reported SSD capacity instead of infinite by @Oxygen56 in https://github.com/kvcache-ai/Mooncake/pull/2278
• [TE][Store] Fix IPv6 address parsing in connection endpoints by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2184
• Fix P2PHANDSHAKE in dual-NIC container setups via MC_RDMA_BIND_ADDRESS by @stmatengss with @Copilot in https://github.com/kvcache-ai/Mooncake/pull/2280
• [TE] IntraNode NVLink transport: update cuMemcpyAsync to BatchAsyc for CUDA version >= 12.8 by @TTThanos in https://github.com/kvcache-ai/Mooncake/pull/2251
• fix(wheel): exclude libfabric/libefa from auditwheel bundle to avoid dual-libfabric EFA conflict by @whn09 in https://github.com/kvcache-ai/Mooncake/pull/2271
• remote redis dependency by @jinke446 in https://github.com/kvcache-ai/Mooncake/pull/2109
• [Store] Robustify ConfigDict size parsing by @CAICAIIs in https://github.com/kvcache-ai/Mooncake/pull/2206
• fix: unify default cluster_namespace to match master's DEFAULT_CLUSTE… by @leonzzhu in https://github.com/kvcache-ai/Mooncake/pull/2244
• [TE] fix: pass default port when parsing TENT RDMA bind a… by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2289
• [Store] RemoveAll not deleting SSD offload files, enable storage_backend_->RemoveAll() in Client::RemoveAll by @Colors-111 in https://github.com/kvcache-ai/Mooncake/pull/2283
• [Store] Propagate tenant identity through object RPCs by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2288
• [Doc] add vLLM scenario-based landing pages and archive legacy docs by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2262
• [Store] Support tenant-aware async storage tasks by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2294
• [Build] Disable debug symbols (-g) in default compilation flags by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2285
• [TE] Fix TCP connection pool SIGSEGV by deferring cleanup with asio::post by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2174
• Store Extract 3FS logic into DistributedStorageBackend by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/2234
• [TENT] Add policy name binding to transport selector by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2295
• [Doc] reorganize API reference with Python/C++/HTTP sub-indices by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2263
• [Store] Support SSD offload configuration in standalone store service by @ertcmm in https://github.com/kvcache-ai/Mooncake/pull/2261
• [TransferEngine] Make TCP transport slice size configurable via MC_TCP_SLICE_SIZE by @gogongxt in https://github.com/kvcache-ai/Mooncake/pull/2308
• fix(transfer_engine): improve auto gid selection and retry by @Bo-Vincent in https://github.com/kvcache-ai/Mooncake/pull/2269
• [TE/TENT] Allow building tebench without USE_TENT by @00fish0 in https://github.com/kvcache-ai/Mooncake/pull/2322
• fix(ci): move sccache --show-stats to after build steps by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2303
• [Docs][1/N] Refactor Readme: update readme top link and badges by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/2304
• [Docs] [2/N] Refactor Readme: merges the Showcase and Components sections by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/2312
• [TE] fix(efa): short-circuit same-process GPU loopback to avoid libfabric SHM segfault by @whn09 in https://github.com/kvcache-ai/Mooncake/pull/2298
• [Doc] Update Documentation URL in pyproject.toml by @ShangmingCai in https://github.com/kvcache-ai/Mooncake/pull/2326
• [Docs] Add build guidance for npu platform by @VNightMare in https://github.com/kvcache-ai/Mooncake/pull/2325
• [Store] Fix idempotent rpc_meta re-publish by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2311
• [Bugfix][Store] Fix HA snapshot restore rejecting newer metadata formats by @Dao007forever in https://github.com/kvcache-ai/Mooncake/pull/2257
• [TE] Optimize ascend_direct async query and fix auto_connect teardown by @ascend-direct-dev in https://github.com/kvcache-ai/Mooncake/pull/2323
• [TransferEngine] Fix resource leaks in error paths by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2332
• [Common] Harden Environ parsing, fix opendir leak, support .yml config by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2316
• [PG] Add MUSA build support by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/2329
• [Wheel] Fix _parse_segment_size to support KB/MB/TB suffixes and fix handle_put None crash by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2321
• [TE] add device API support by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/2333
• [PG] Fix null-deref on MNNVL disconnect and activeRanks leak by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2347
• [PG] Fix data race: make running_ atomic by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2352
• [PG] Build the MUSA PG extension through torchada by @yeahdongcn in https://github.com/kvcache-ai/Mooncake/pull/2353
• Fix DLSlime typo in LMDeploy docs by @JimyMa in https://github.com/kvcache-ai/Mooncake/pull/2356
• feat(engine): add attributes in python package for compile flags by @HubertZhang in https://github.com/kvcache-ai/Mooncake/pull/2342
• [Doc] Add Mooncake local CI skill docs by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2134
• [TENT] Validate minimum request size before XferDataDesc cast by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2351
• [TE] Fix data race, double-close, uninit, and off-by-one in RDMA transport by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2346
• [TE] Harden config parsing: remove exit() and guard stoi by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2344
• [TE] Fix error-path safety: freeaddrinfo leak, null deref, OOB read by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2343
• [TE] Fix lock leak, missing transport_, and empty entries UB by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2349
• feat(store): add NoF SSD deployment tools and e2e coverage by @Enigmo-x in https://github.com/kvcache-ai/Mooncake/pull/2273
• [TE] Harden TCP transport: validate remote addresses, fix idle cleanup, add TCP_NODELAY by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2314
• [Store] master log journal by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2297
• [Store] Remove HAMetricManager::Init() by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2287
• [Store] Clean up tenant-aware master service APIs by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2337
• [TENT] feat: add per-request transport_hint for fine-grained transport selection in tent by @chestnut-Q in https://github.com/kvcache-ai/Mooncake/pull/2339
• [Store] Introduce buffer pool for zero copy interfaces by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2095
• chore(Doc): update clang-format installation instructions in documentation by @SYaoJun in https://github.com/kvcache-ai/Mooncake/pull/2381
• [Doc] restructure SGLang integration docs and add performance index by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2265
• [build] NPU wheel: RPATH patching, vendored lib consolidation, pip retry, cmake fixes by @JieTang66 in https://github.com/kvcache-ai/Mooncake/pull/2216
• [Store] feat: add GetSegmentsDetail API to expose segment info via ad… by @leonzzhu in https://github.com/kvcache-ai/Mooncake/pull/2310
• [Common][Store][TE] Fix UB: passing signed char to ::tolower in std::transform by @Chelseatr in https://github.com/kvcache-ai/Mooncake/pull/2367
• [CI] Add issue bot for auto-triage and stale issue closure by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2378
• [Doc] rewrite deployment guide and add Mooncake Store performance index by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2266
• [TENT] Add local admission queue prototype by @zbchi in https://github.com/kvcache-ai/Mooncake/pull/2341
• [TE] Improving the RDMA transport failure handling by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2155
• [TransferEngine] Fix: TCP transport implicitly creates CUDA context on GPU0 by @gogongxt in https://github.com/kvcache-ai/Mooncake/pull/2307
• Add modular KVCache storage benchmark (v1) by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2368
• [Doc] finalize navigation restructure and update build/design docs by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2267
• [Store] Introduce cached batch query result by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/1834
• [CI] guard sccache stats when unavailable by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2369
• feat: support graceful shutdown for mooncake_master on SIGINT/SIGTERM by @SYaoJun in https://github.com/kvcache-ai/Mooncake/pull/2359
• [TE] Guard stoull in EFA getMaxPteEntries against invalid input by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2363
• [Docs] [3/N] Refactor Readme: improve TE description and streamline updates by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/2418
• [CI] allow clang-format (generic binary) to be detected as version 20 by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2334
• [Integration] Reject failed Python buddy allocator backing buffer by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2402
• [Docs] move Mooncake Store usage guide by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2421
• fix(ha): ensure /oplog/{cluster_id}/latest key is initialized on firs… by @leonzzhu in https://github.com/kvcache-ai/Mooncake/pull/2168
• [Docs] [4/N] Refactor Readme: simplify hardware and build sections by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2420
• [Misc] Enhance PR template with AI disclosure and structured testing by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2397
• [TE] Use MLU address range query for RDMA dmabuf by @phantomlei3 in https://github.com/kvcache-ai/Mooncake/pull/2416
• [CI/Build] Expand auto-labeling and add PR description cleanup by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2396
• [TE] fix race condition in ub_transport and disable ub_transport_test by @00fish0 in https://github.com/kvcache-ai/Mooncake/pull/2324
• [TE] Fix NVMeoF loop variable bug and NVMeoFBatchDesc leak by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2373
• [TransferEngine] Bound handshake-port connect() with a timeout by @Dao007forever in https://github.com/kvcache-ai/Mooncake/pull/2425
• [PG] Add experimental MACA PG support by @Dayuxiaoshui in https://github.com/kvcache-ai/Mooncake/pull/2365
• [Docs] Readme add pypi npu badge by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/2437
• [TransferEngine] fix: reset last_wait_ts after work to avoid skipping… by @QAQYangT-T in https://github.com/kvcache-ai/Mooncake/pull/2434
• [TransferEngine] Clean up failed io_uring sub-batch initialization by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2403
• feat(store): scope S3 snapshot path by cluster_id to support multi-cl… by @leonzzhu in https://github.com/kvcache-ai/Mooncake/pull/2301
• [Store] fix: register local hot cache memory with transfer engine by @zwtao40 in https://github.com/kvcache-ai/Mooncake/pull/2399
• [CI] Change options to speed up ci for ascend. by @VNightMare in https://github.com/kvcache-ai/Mooncake/pull/2439
• [Doc] Fix inaccuracies in EFA transport doc (vLLM router, SGLang patch link, Technical Details) by @whn09 in https://github.com/kvcache-ai/Mooncake/pull/2443
• [build] Migrate NPU wheel CI to cloud runners with ARM/x86 matrix by @JieTang66 in https://github.com/kvcache-ai/Mooncake/pull/2386
• [TE][Sunrise][Feat] Enable Sunrise support in the classic transfer engine path by @RuixiangMa in https://github.com/kvcache-ai/Mooncake/pull/2290
• [Docs] [5/N] Refactor Readme: Streamline README Store, SGLang, and vLLM integration sections by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/2442
• [EP] integrate Device API (P2pTransport/RdmaTransport) — CUDA only by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/2382
• [Store] test: add comprehensive MasterAdminServer HTTP endpoint tests by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2431
• [CI] add qoder review by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2462
• [Store] fix: /query_key endpoint returns valid JSON response by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2435
• Store check actual disk space in eviction logic by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/2419
• [CI] Skip Qoder code review for fork and cross-repo PRs by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2473
• [Integration] Return documented failure sentinel 0 from uint64 async transfer APIs by @bp-cheng in https://github.com/kvcache-ai/Mooncake/pull/2433
• fix: wrap async main() for console_scripts entry point by @mzygQAQ in https://github.com/kvcache-ai/Mooncake/pull/2453
• [TE] Extend standalone same-device avoidance to non-RoCE paths by @ascend-direct-dev in https://github.com/kvcache-ai/Mooncake/pull/2366
• [Store] Fix local hot cache rejecting larger objects after block reuse by @feichai0017 in https://github.com/kvcache-ai/Mooncake/pull/2466
• [Docs] Fix onboarding bugs: NameError, Dockerfile ref, PyPI URL, missing deps by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2408
• [Docs]: Document group semantics by @yokinoshitayoki in https://github.com/kvcache-ai/Mooncake/pull/2465
• [Store] feat: add tenant quota core by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2358
• [TE][Sunrise][Feat] Enable Sunrise VRAM support in tebench for the TENT backend by @RuixiangMa in https://github.com/kvcache-ai/Mooncake/pull/2452
• [docs] add docs for EP & PG by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/2481
• [Store] Fix stale hot cache reuse after object removal by @zchuango in https://github.com/kvcache-ai/Mooncake/pull/2447
• [build] Add Python 3.9 support to NPU wheel release by @JieTang66 in https://github.com/kvcache-ai/Mooncake/pull/2483
• [Store] fix: change default eviction policy for offload bucket from n… by @NUABO in https://github.com/kvcache-ai/Mooncake/pull/2474
• fix(efa): declare FI_HMEM in caps for GPU builds by @whn09 in https://github.com/kvcache-ai/Mooncake/pull/2448
• [Store] Fix ABBA deadlock between GracefulUnmountScheduler and snapshot_mutex_ by @feichai0017 in https://github.com/kvcache-ai/Mooncake/pull/2486
• [CI/Build] Add stale issue/PR bot by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2395
• [Bugfix] Support EulerOS in dependencies installer by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2460
• [Store][Refactor]: extract generic DeadlineScheduler from graceful unmount by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2494
• [Doc]: publish built-in skills and add plugin marketplace by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2497
• [Store] support zero-sized tensors in Python APIs by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2470
• [Store] Reduce lookup eviction contention by @yokinoshitayoki in https://github.com/kvcache-ai/Mooncake/pull/2405
• fix(store): don't fail bundle cleanup when per-key remove retry succeeds by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2500
• [Integration] Fix double-free in buffer_to_tensor error path by @feichai0017 in https://github.com/kvcache-ai/Mooncake/pull/2493
• [TENT] Reduce SegmentDesc fetch overhead on cold receive path by @chestnut-Q in https://github.com/kvcache-ai/Mooncake/pull/2482
• [CI] cleanup: delete deprecated .ci directory by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2517
• [TE] Add MC_TE_FILTERS env var for IB device whitelist by @huojianqiangg in https://github.com/kvcache-ai/Mooncake/pull/2495
• [Doc] Update tent arxiv paper to README.md by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2522
• [Store] Group BatchGetReplicaList metadata lookup by shard by @bitborne in https://github.com/kvcache-ai/Mooncake/pull/2508
• Store: Enable rpc timeout by @zhangzuo21 in https://github.com/kvcache-ai/Mooncake/pull/2423
• [Store] recover etcd client after leader hang (SIGSTOP) by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/2383
• [Store] Make etcd master-view watch event-driven instead of polling by @silas-scitix in https://github.com/kvcache-ai/Mooncake/pull/2484
• [Store][Refactor]: Refactor master admin service by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2422
• [Store] Rust: don't force-link the ASan runtime in non-sanitized builds by @donghun-furiosa in https://github.com/kvcache-ai/Mooncake/pull/2510
• [Store] Fix cache total metrics accounting on metadata removal by @feichai0017 in https://github.com/kvcache-ai/Mooncake/pull/2520
• [Store][TE] Fix remaining signed-char ::tolower/::toupper UB missed by [#2367] by @bp-cheng in https://github.com/kvcache-ai/Mooncake/pull/2488
• [TE] Fix signed-char tolower UB in PCI BDF lowercasing loops (follow-up to [#2367]/#2488) by @bp-cheng in https://github.com/kvcache-ai/Mooncake/pull/2504
• [TENT] Fix CUDA event leak in nvlink/mnnvl transports by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2507
• [EP] support MUSA platform by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/2480
• [CI] disable automatic assignment by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2531
• [TE] Support per-role Ascend protocol for co-located Transfer Engines by @ascend-direct-dev in https://github.com/kvcache-ai/Mooncake/pull/2499
• Add torch 2.12.1 to EP PG build matrix by @mmangkad in https://github.com/kvcache-ai/Mooncake/pull/2538
• [CI] Update stale.yml by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2543
• [Store] dynamic tenant quota master admission by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2492
• [Store] add codec inference and recursive structure expansion by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2521
• [Doc] Rework Mooncake Store deployment guide: P2P-first quick start, three client deployment methods, flag fixes by @00fish0 in https://github.com/kvcache-ai/Mooncake/pull/2532
• [TE][Fix] Fix excessive memory allocation in submitPostSend by @leonzzhu in https://github.com/kvcache-ai/Mooncake/pull/2490
• [TE] fix(efa): widen MR keys to 64-bit to avoid fi_mr_key() truncation by @whn09 in https://github.com/kvcache-ai/Mooncake/pull/2564
• [Store] Complete dynamic tenant quota admin, eviction, metrics, and snapshots by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2549
• [Doc] complete Rust API reference for transfer engine and mooncake store by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2547
• [Store][K8s-Native][3/N] Label-based routing by @vladnosiv in https://github.com/kvcache-ai/Mooncake/pull/2537
• Update BatchAsync for MMNVL by @TTThanos in https://github.com/kvcache-ai/Mooncake/pull/2384
• [Store] Add size-class allocator fragmentation benchmark by @HGinkgo in https://github.com/kvcache-ai/Mooncake/pull/2340
• [TENT] add local runtime queue dispatch by @zbchi in https://github.com/kvcache-ai/Mooncake/pull/2562
• [Store] fix integer overflow in BatchOffload for objects larger than 4 GiB by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2570
• HipTransport: restore caller device after async transfer by @carlushuang in https://github.com/kvcache-ai/Mooncake/pull/2566
• [CI] Fix build-musa: add missing MUSA macro mappings for nvlink_tranport APIs by @RuixiangMa in https://github.com/kvcache-ai/Mooncake/pull/2575
• [TE] Make TransferEngine movable by @zjjf in https://github.com/kvcache-ai/Mooncake/pull/2567
• [TransferEngine] Apply configured SL/TC to the TENT notification QP by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2526
• [Store] add structured object copy-mode policy by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2472
• [Store]: Fix BatchEvict Over-Eviction Due to Inflated Target When SSD Offload Is Enabled by @Colors-111 in https://github.com/kvcache-ai/Mooncake/pull/2286
• [Store] Clean up HTTP metadata on client timeout for separately-deployed metadata servers (follow-up to [#1363]) by @chenkaiyue in https://github.com/kvcache-ai/Mooncake/pull/2498
• [Bugfix] Preserve empty values in Mooncake Store REST GET by @VectorPeak in https://github.com/kvcache-ai/Mooncake/pull/2587
• [TE] Universal TCP Force Mechanism for All Environments by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2593
• [Build] Fix build failure on Python 3.14t without --enable-shared by @leveretconey in https://github.com/kvcache-ai/Mooncake/pull/2553
• [Store] Add SSD free-ratio-first allocation strategy by @zchuango in https://github.com/kvcache-ai/Mooncake/pull/2450
• [Store][Bugfix]:Fix SGLang fails to start with MC_USE_TENT=1 when built without USE_TENT by @RuixiangMa in https://github.com/kvcache-ai/Mooncake/pull/2596
• [TransferEngine] Make InfiniBand Service Level configurable via MC_IB_SL by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2525
• [TE] Skip redundant Disconnect on AutoConnect transfer failures by @ascend-direct-dev in https://github.com/kvcache-ai/Mooncake/pull/2604
• fix(rdma): restore task.request association in submitTransfer by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2610
• [codex] sync store and benchmark docs by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2556
• [MUSA] Add release-musa github workflow by @yeahdongcn in https://github.com/kvcache-ai/Mooncake/pull/2576
• [Store] add structured object flat mvp by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2600
• [TE] Enforce one-shot lifecycle for connected RDMA endpoints by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2588
• fix(maca): map cudaStreamQuery for the intra-node NVLink build by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2606
• [Store] Make offloading_queue_limit and offload_cap_ratio configurabl… by @leonzzhu in https://github.com/kvcache-ai/Mooncake/pull/2599
• [Doc] chore: Add Sunrise logo to supported hardware and contributors by @RuixiangMa in https://github.com/kvcache-ai/Mooncake/pull/2615
• Infer gpu device from request source pointers, set correct device for stream creation. by @dadadada-147 in https://github.com/kvcache-ai/Mooncake/pull/2569
• [PG] Fix elastic P2P after max_world_size recovery by @zackyoray in https://github.com/kvcache-ai/Mooncake/pull/2623
• [CI] Add AWS EFA wheel build/release to official CI/CD by @whn09 in https://github.com/kvcache-ai/Mooncake/pull/2565
• [TE] Fix signed-char isxdigit UB in EFA smaps page-size parsing (follow-up to [#2504]) by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2619
• fix(transport): associate task.request in EFA/Kunpeng submitTransfer by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2617
• [CI][Build] Build CUDA release wheels in the PyTorch manylinux image by @mgoin in https://github.com/kvcache-ai/Mooncake/pull/2605
• [Store] add remote tensor batch interfaces by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2050
• [Bugfix] Parse string booleans for enable_ssd_offload in from_file by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2506
• [Docs] Clarify non-CUDA quick start dependencies by @Makzert in https://github.com/kvcache-ai/Mooncake/pull/2539
• [Bugfix] Return HTTP 500 when is_exist reports an error in handle_exist by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2602
• [CI] Disable pip cache in build-flags to avoid disk exhaustion by @mgoin in https://github.com/kvcache-ai/Mooncake/pull/2626
• [Store] Stop snapshot thread promptly during shutdown by @feichai0017 in https://github.com/kvcache-ai/Mooncake/pull/2533
• [Bugfix] Fix RDMA active handshake timeout race with simultaneous passive connection by @LCAIZJ in https://github.com/kvcache-ai/Mooncake/pull/2624
• [TENT] Add optional Request.deadline_ns and MLU observability metric (RFC [#2519] step 1) by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2618
• [Store] Don't abort client init on a malformed MC_MS_AUTO_DISC value by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2629
• [Bugfix] Set Ascend context in batch get worker by @greatwhole in https://github.com/kvcache-ai/Mooncake/pull/2557
• [Doc] chore: Add Hygon logo to supported hardware and contributors by @huojianqiangg in https://github.com/kvcache-ai/Mooncake/pull/2642
• [TransferEngine] Guard MC_TCP_SLICE_SIZE parsing against std::stoull throwing by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2641
• [Docs] [7/N] Refactor Readme: update README hardware partners table and logos by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/2654
• [Store] Fix source refcnt leak in CopyEnd/MoveEnd on invalid source by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2628
• Hca peer affinity by @hzt123123 in https://github.com/kvcache-ai/Mooncake/pull/2616
• [TE] Guard against null endpoint_store_ in UrmaContext destructor by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2627
• [TE] add HPE Slingshot (cxi) backend by @wqwqazwsxedc in https://github.com/kvcache-ai/Mooncake/pull/2535
• [TENT] Fix stale getTransferStatus in nvlink/mnnvl/ascend transports by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2505
• [EP] Fix: Skip inactive ranks in combine reduction loop by @RuixiangMa in https://github.com/kvcache-ai/Mooncake/pull/2653
• [Docs] Add Docker Badge for Readme by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/2670
• [build] Use dynamic CANN version detection for NPU release workflow by @JieTang66 in https://github.com/kvcache-ai/Mooncake/pull/2577
• [TE] Name AscendDirectTransport worker threads by @ascend-direct-dev in https://github.com/kvcache-ai/Mooncake/pull/2672
• [Docs] [6/N] Refactor Readme: Streamline README and move setup/trace details to other places by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/2652
• [Store] feat: implements strict multi-tenant quota admission by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2612
• [CI] add arm64 CI by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/2428
• [Store] Skip bucket files with non-numeric names instead of aborting Init by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2651
• [TENT] Port TE RDMA lifecycle and tests to TENT by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2664
• [Bugfix] Remove duplicate replica erase in PutRevoke by @fcczzz in https://github.com/kvcache-ai/Mooncake/pull/2679
• [EP]:Stabilize MACA Expert Parallelism P2P Fast Path by @Dayuxiaoshui in https://github.com/kvcache-ai/Mooncake/pull/2592
• [Docs] Update build guide source flow by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2675
• [Store] Refactor accelerator device registry and staging copies by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2583
• [Store]: Fix Offloading Task Orphan Causing Expired Warnings by @Colors-111 in https://github.com/kvcache-ai/Mooncake/pull/2658
• Complete Cache Hit Metrics for Memory and SSD Offload Tiers by @Colors-111 in https://github.com/kvcache-ai/Mooncake/pull/2637
• [TE] Support rdma+hip multi-protocol segments for single-node disaggregation by @Lzy17 in https://github.com/kvcache-ai/Mooncake/pull/2682
• [Doc]: clarify Mooncake Store quick start and Transfer Engine guidance by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2667
• [Doc] Align docs homepage and sidebar navigation depth by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2705
• [Bugfix] Separate post and poll in RDMA worker pool by @c-guo16 in https://github.com/kvcache-ai/Mooncake/pull/2696
• [Store] Refactor SHM UDS FD Passing for Real/Dummy Client by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2681
• [Wheel] Enrich PyPI metadata for Mooncake wheel variants by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/2677
• Apply per Device stream to avoid GPU 0 kmd traffic by @TTThanos in https://github.com/kvcache-ai/Mooncake/pull/2578
• [Store][Sunrise]: Enable sunrise support for Mooncake Store by @RuixiangMa in https://github.com/kvcache-ai/Mooncake/pull/2534
• Bump google.golang.org/grpc from 1.59.0 to 1.79.3 in /mooncake-p2p-store/src/p2pstore by @dependabot[bot] in https://github.com/kvcache-ai/Mooncake/pull/1789
• [CI] fix some small CI issues by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/2686
• [Store] Add Local First Allocation Strategy by @yokinoshitayoki in https://github.com/kvcache-ai/Mooncake/pull/2638
• [Store] Add NormalizeTenantIdRef zero-copy variant for hot paths by @ZhijunLStudio in https://github.com/kvcache-ai/Mooncake/pull/2698
• [CI/Build] Fix build-musa: add missing MUSA mappings for nvlink_transport APIs (#2578) by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/2710
• [TE] Fix cross-node RDMA KV transfer under rdma+hip multi-protocol on AMD by @Lzy17 in https://github.com/kvcache-ai/Mooncake/pull/2725
• [CI] publish master image to Docker Hub via manual workflow by @tpiperatgod in https://github.com/kvcache-ai/Mooncake/pull/2678
• [Doc] Clarify FAST25 trace release by @yokinoshitayoki in https://github.com/kvcache-ai/Mooncake/pull/2727
• [TE] Capture GPU device at registration time in MnnvlTransport / NVLinkTransport by @xiangui33423 in https://github.com/kvcache-ai/Mooncake/pull/2691
• fix(store): chunk oversized io_uring vector I/O by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2719
• Bump golang.org/x/net from 0.47.0 to 0.55.0 in /mooncake-common/k8s-lease by @dependabot[bot] in https://github.com/kvcache-ai/Mooncake/pull/2742
• [TE] Add TPU (PJRT) staging support to TENT by @Liwink in https://github.com/kvcache-ai/Mooncake/pull/2733
• [Store] Make batch_query_keys read-only and return all replica types by @smartssw in https://github.com/kvcache-ai/Mooncake/pull/2685
• [Doc] Add agent guidance by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2712
• [TransferEngine] Prefer private-range IPv4 GIDs over link-local IPv6 in auto-selection by @n-WN in https://github.com/kvcache-ai/Mooncake/pull/2741
• [TE] Downgrade unrecognized mem addr log from ERROR to INFO by @ascend-direct-dev in https://github.com/kvcache-ai/Mooncake/pull/2734
• [Store] Enable hugepage mmap in allocate_buffer_numa_segments by @mikegguo in https://github.com/kvcache-ai/Mooncake/pull/2417
• [TENT] Fix data race on local SegmentDesc via copy-on-write snapshots by @n-WN in https://github.com/kvcache-ai/Mooncake/pull/2714
• [Store] Format Mooncake Store Go and Rust bindings by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2737
• [TE] Fix MNNVL staging path reading capabilities from RDMA transport by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/2751
• [Store] add etcd tenant quota connector by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2687
• [Store] Fix ConfigDict global segment size validation by @bitborne in https://github.com/kvcache-ai/Mooncake/pull/2661
• [Store] Refactor store buffer headers and slice splitting by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2732
• [TENT] SelectionPolicy: per-policy SL/TC/qp_pool schema (RFC [#2568] step 1) by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2640
• [Store] feat: allow configuring client tenant id by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2755
• [TE] Fix cross-GPU NVLink/MNNVL event-stream device mismatch (#2722) by @xiangui33423 in https://github.com/kvcache-ai/Mooncake/pull/2754
• [TE] Route cross-host targets over rdma automatically in rdma+hip multi-protocol segments by @Lzy17 in https://github.com/kvcache-ai/Mooncake/pull/2753
• Bump golang.org/x/net from 0.38.0 to 0.55.0 in /mooncake-transfer-engine/example/http-metadata-server by @dependabot[bot] in https://github.com/kvcache-ai/Mooncake/pull/2730
• [CI/Build] Add dedicated tent-ci job with CUDA/CPU matrix by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/2720
• [Doc] Update README with LightX2V deployment details by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2767
• [Store] Add BatchEvict candidate-selection benchmark by @jacklin78911-collab in https://github.com/kvcache-ai/Mooncake/pull/2584
• docs: clarify local SSD offload configuration by @feichai0017 in https://github.com/kvcache-ai/Mooncake/pull/2728
• [Wheel] Validate MooncakeConfig fields with fail-fast errors by @SuperMarioYL in https://github.com/kvcache-ai/Mooncake/pull/2456
• [Store] Externalize S3 client config via environment variables by @mzygQAQ in https://github.com/kvcache-ai/Mooncake/pull/2649
• [TENT] Per-pool QP allocation with per-pool SL/TC (RFC [#2568] step 2) by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2759
• [TENT] Make RDMA NIC allow/deny list configurable via MC_FILTER_NIC(_EXCLUDE) by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2760
• [CI] Extract reusable wheel build/publish workflows by @mgoin in https://github.com/kvcache-ai/Mooncake/pull/2723
• [Store] Support local_buffer_size in mooncake_client by @NUABO in https://github.com/kvcache-ai/Mooncake/pull/2739
• [TENT] Opt-in earliest-deadline-first dispatch in admission queue (RFC [#2519] step 2) by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2763
• [Bench] Enable replay speedup and multi-threading in SSD Benchmarking by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2780
• [TENT] Deadline-infeasible drop + degradation hook (RFC [#2519] step 3) by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2764
• [Store] Fix S3 list objects pagination by @feichai0017 in https://github.com/kvcache-ai/Mooncake/pull/2778
• feat(store): add optional RFC [#1527] KV events publisher on master by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2214
• [TENT] RailMonitor: prefer same-name device for cross-NUMA rail mapping (#2758/#2467) by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2790
• Bump golang.org/x/net from 0.48.0 to 0.55.0 in /mooncake-p2p-store/src/p2pstore by @dependabot[bot] in https://github.com/kvcache-ai/Mooncake/pull/2708
• [Bugfix] Reject empty keys in HTTP metadata server by @VectorPeak in https://github.com/kvcache-ai/Mooncake/pull/2770
• [wip] docs: add vLLM V1 MooncakeStore KV cache sharing benchmark by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/2773
• Bump golang.org/x/crypto from 0.51.0 to 0.52.0 in /mooncake-transfer-engine/example/http-metadata-server by @dependabot[bot] in https://github.com/kvcache-ai/Mooncake/pull/2789
• [Store] Fix --host parameter to support ip:port format for TransferEngine data plane port by @NUABO in https://github.com/kvcache-ai/Mooncake/pull/2784
• [TENT] Opt-in per-entry priority promotion (#2528) by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2788
• [TENT] Expose Request.deadline_ns and policy_name to Python bindings by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2808
• [Bugfix][TENT] Fix silent TPU data corruption for transfers larger than one staging chunk by @Liwink in https://github.com/kvcache-ai/Mooncake/pull/2815
• [Doc] Reorganize performance docs by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/2824
• [Bugfix] Skip os.chmod when binary is already readable and executable by @Csrayz in https://github.com/kvcache-ai/Mooncake/pull/2803
• [CI/Build] Fix compile warnings by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2825
• [Store] Refactor: Extract snapshot orchestration into MasterSnapshotManager by @xiangui33423 in https://github.com/kvcache-ai/Mooncake/pull/2805
• [TENT] Add IntentType enum to Request for Transfer Intent API by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2810
• [TENT] admission queue: deadline proximity promotion for dispatch by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2814
• [TransferEngine] Add show-link diagnostic tool for NIC topology by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2820
• [TransferEngine] Add graceful shutdown for SIGTERM/SIGINT by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2812
• [TransferEngine] Validate batch memory registrations by @feichai0017 in https://github.com/kvcache-ai/Mooncake/pull/2854
• [TE] Make ThreadLocalStorage per-instance and reclaim per-thread holders by @n-WN in https://github.com/kvcache-ai/Mooncake/pull/2842
• [EP] Cap active RoCE QPs for IBGDA kernels by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/2544
• [EP] add DeepEP V2 elastic buffer by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/2503
• [TE] Add host control fallback for IBGDA QP setup by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/2867
• [CI] Migrate tone_tests to CUDA 13: pull cu130 wheel, adapt sglang/vllm paths, add NCCL env & offline model cache by @luketong777 in https://github.com/kvcache-ai/Mooncake/pull/2811
• [TransferEngine] Acknowledged TCP framing: COMPLETED means applied at destination by @n-WN in https://github.com/kvcache-ai/Mooncake/pull/2850
• [TransferEngine] Reject concurrent overlapping memory registrations by @feichai0017 in https://github.com/kvcache-ai/Mooncake/pull/2870
• [TransferEngine] Optimize MACA P2P copy path by @Dayuxiaoshui in https://github.com/kvcache-ai/Mooncake/pull/2774
• [Store] Speed up HugeTLB population before RDMA registration by @zhangzuo21 in https://github.com/kvcache-ai/Mooncake/pull/2838
• [TE] Fix RDMA transport rail-failure handling and CQ timeout diagnostic by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2872
• [TENT] Add best-effort RDMA task cancellation by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2851
• [Bugfix] Gate RDMA sends until active side confirms QP readiness by @LCAIZJ in https://github.com/kvcache-ai/Mooncake/pull/2625
• [Store] feat: expose client metrics HTTP config to Python by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2822
• [TENT] Add causal chain stage decomposition for transfer latency by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2821
• [TE] Add metadata refresh polling for segment cache by @greatwhole in https://github.com/kvcache-ai/Mooncake/pull/2795
• [TENT] Bind transport policies to intent type by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2847
• [store] Opt-in topology-aware remote replica scoring in SelectBestReplica (#2516) by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2781
• [Store] Extract master snapshot codec from MasterService（3/5） by @xiangui33423 in https://github.com/kvcache-ai/Mooncake/pull/2831
• [TENT] Opt-in deadline-aware NIC bandwidth arbitration (RFC [#2792]) by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2794
• [Transfer Engine] Refresh RDMA metadata on HCA and GID change events by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2878
• [Doc] Add Kubernetes Deployment Guide for Mooncake Store and Transfer Engine by @tpiperatgod in https://github.com/kvcache-ai/Mooncake/pull/2771
• [Store] Fix SSD offload publish-before-commit race (#2799) by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/2818
• [STORE] Implement FIFO eviction for OffsetAllocatorStorageBackend by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/2880
• [TENT] Reuse and release SHM relocation mappings across threads by @morluto in https://github.com/kvcache-ai/Mooncake/pull/2891
• [TE] Reject empty RDMA completion resources during context setup by @morluto in https://github.com/kvcache-ai/Mooncake/pull/2892
• [Store] Tune Master defaults based on RPC scaling results by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2871
• [TENT] Wire live RDMA bandwidth into admission queue degradation policy by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2816
• [TE] Use std::atomic to support ARM64 relaxed ordering by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2897
• [TE] Reject unsupported NVMe-oF task batches and correlate cuFile completions by @morluto in https://github.com/kvcache-ai/Mooncake/pull/2893
• [Store] Make batch_evict_bench scale and eviction ratios configurable by @jacklin78911-collab in https://github.com/kvcache-ai/Mooncake/pull/2855
• [TENT] Add receiver-credit ledger model and protocol invariants by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2860
• [TENT] Add QoS metrics baseline to tebench by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2845
• [TENT] Fix mismatched cuFileBatchIOGetStatus semantics in gds transport by @tong1heng in https://github.com/kvcache-ai/Mooncake/pull/2921
• [Store] fix GPU-addressed local copy crashes by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2926
• [Doc] Update README news by @stmatengss with @Copilot in https://github.com/kvcache-ai/Mooncake/pull/2940
• [TransferEngine] Share one dma_buf fd across all NICs to avoid ×N BAR1 usage by @Dao007forever in https://github.com/kvcache-ai/Mooncake/pull/2523
• [Store] Extract snapshot restore path into layered architecture（4/5） by @xiangui33423 in https://github.com/kvcache-ai/Mooncake/pull/2879
• feat(store): add proactive disk watermark eviction by @CAICAIIs in https://github.com/kvcache-ai/Mooncake/pull/2281
• [TENT] Add QoS contract schema resolver by @catyans in https://github.com/kvcache-ai/Mooncake/pull/2857
• [store] fix SPDK client buffer teardown by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2936
• [transport/nvmeof] surface terminal slice failures by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2939
• [MUSA] Enable EP/PG extensions by switching to a PyTorch base image by @yeahdongcn in https://github.com/kvcache-ai/Mooncake/pull/2938
• [TE] Enforce QP teardown before MR dereg on shutdown by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2895
• [TransferEngine] Propagate batch memory operation errors by @feichai0017 in https://github.com/kvcache-ai/Mooncake/pull/2869
• [Bugfix][TransferEngine] Pause active reconnects to failed peers by @Dao007forever in https://github.com/kvcache-ai/Mooncake/pull/2941
• [TransferEngine] Roll back partial registration in registerLocalMemory by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2965
• [TE] Add MNNVL support to Device API by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/2956
• [Wheel] Gracefully stop Store REST service on SIGTERM by @zhangzuo21 in https://github.com/kvcache-ai/Mooncake/pull/2874
• [Store] Clean up and document snapshot refactoring (5/5) by @xiangui33423 in https://github.com/kvcache-ai/Mooncake/pull/2943
• [Store] Surface HTTP metadata server bind failures in start() by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2942
• [Doc] Add SGLang PD transfer benchmark by @yokinoshitayoki in https://github.com/kvcache-ai/Mooncake/pull/2972
• [Bugfix] Roll back failed OffsetAllocator evictions by @feichai0017 in https://github.com/kvcache-ai/Mooncake/pull/2964
• [CI/Build] Build release aarch64 wheels in a manylinux container by @chethanuk in https://github.com/kvcache-ai/Mooncake/pull/2968
• [CI] Align pre-release artifact names with release naming by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2931
• [CI/Build] Fix pre-release wheel builds by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2975
• [TE] Improve RDMA NIC failover recovery by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/2959
• [TENT] Fix metrics HTTP server falsely reporting success on port bind failure by @anranxia in https://github.com/kvcache-ai/Mooncake/pull/2978
• [CI/Build] Fix test-wheel-ubuntu flake by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/2988
• [Store] Serialize ssd_total_capacity_bytes in local disk snapshot (#2783) by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2927
• [Doc] Add llm-d Integration page to the Kubernetes deployment guide by @tpiperatgod in https://github.com/kvcache-ai/Mooncake/pull/2983
• [CI/Build] Disable unit tests in release wheel builds by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2995
• [Store] L2→L1 promotion background retry for hot LOCAL_DISK-only keys (V1.1) by @Srinivasoo7 in https://github.com/kvcache-ai/Mooncake/pull/2690
• [PG][1/N] Decouple communication failures from membership changes by @caozhanhao in https://github.com/kvcache-ai/Mooncake/pull/2338
• [CI/Build] Stabilize release wheel builds by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3002
• [TENT] Expose RDMA NIC load stats via Transport interface by @HeinUmin in https://github.com/kvcache-ai/Mooncake/pull/2996
• [TENT] Fix metrics recording zero-overhead, MLU sentinel, and parallel-vector contract by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/2989
• Revert "[PG][1/N] Decouple communication failures from membership changes" by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3011
• feat: expand Grafana dashboard with comprehensive Master metrics panels by @liangxu2000 in https://github.com/kvcache-ai/Mooncake/pull/2944
• [TENT] Remove dead metrics config flags and wire validateConfig into initialize() by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/3017
• [CI]fix(ci): lookup integration artifact by workflow run by @luketong777 in https://github.com/kvcache-ai/Mooncake/pull/3026
• [wheel ]feat: add schema-guided DataProto field encoding by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2907
• [CI] Update pull request permissions in workflow by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/3037
• [wheel] add pool-backed structured object reads by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3023
• [CI/Build] Limit EFA release build parallelism by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3045
• [wheel] add unified structured-object put/get API by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3013
• [TENT] Add transport labels to metrics for per-transport observability by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/3029
• [CI] disable qoder auto approve by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/3046
• [CI] Run tests on release branches by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3049
• [wheel] add multi-buffer structured object puts by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3024
• [Store] pin host segments with quota by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2945
• [Store] Introduce canonical TenantId by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2894
• [Store] OffsetAllocator: survive restarts with configurable persistence by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/2932
• [Bugfix][Store] Reject invalid metadata client IDs by @VectorPeak in https://github.com/kvcache-ai/Mooncake/pull/2990
• Fix/verbs api plog error printing by @RuiqingFeng in https://github.com/kvcache-ai/Mooncake/pull/3020
• [CI] Add TENT_METRICS_ENABLED=ON to tent-ci matrix by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/3041
• [Store] Make decode reconfigure remount make-before-break by @SuperMarioYL in https://github.com/kvcache-ai/Mooncake/pull/2884
• [Bugfix][Store] Fix TenantId promotion tests by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3065
• [Doc] Reorganize documentation structure and navigation by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3021
• docs(nvmf): drop the no-op enable_mooncake_nof_pool LMCache key by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/3064
• [CI] Fail fast when T-One GPU cleanup fails by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3036
• [TENT] Unify transportTypeName into types.h as single source of truth by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/3053
• [CI/Build] Pin GoogleTest for reproducible test builds by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2999
• [CI/Build] Prevent CI out-of-space failures by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3005
• Bump version to 0.3.12 in pyproject.toml by @ShangmingCai in https://github.com/kvcache-ai/Mooncake/pull/3081
• [TENT] Add mixed traffic workloads to tebench by @catyans in https://github.com/kvcache-ai/Mooncake/pull/3074
• [Store] Arm the etcd view-change watch once per wait instead of per iteration by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/3062
• [Store] Extract tenant quota table from MasterService by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3071
• [Docs] Correct stale KV lease TTL and eviction high-watermark defaults by @g122622 in https://github.com/kvcache-ai/Mooncake/pull/3022
• [CI/Build] Fix Go setup in MUSA release workflow by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3086
• [Docs] Document multi-model KV cache isolation by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/3082
• [CI/Build] Add MUSA release backfill workflow by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3092
• [Docs] Add pypi badges by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/3103
• [Store] Fix RemoveAll not cleaning SSD offload files on any node via PollRemoveAll RPC by @Colors-111 in https://github.com/kvcache-ai/Mooncake/pull/2676
• [wheel] improve structured non-tensor codecs by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3055
• [wheel] restore zero-copy puts for multi-buffer payloads by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/3054
• [CI] Add torch 2.13.0 to EP build matrix; drop deprecated env_var BUILD_WITH_EP by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3095
• [CI/Build] Fix release wheel ELF layout by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3105
• Bump version to 0.3.12.post1 in pyproject.toml by @ShangmingCai in https://github.com/kvcache-ai/Mooncake/pull/3107
• [CI/Build] Fix CUDA stub release smoke test by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3114
• [TENT] Fix io_uring stale status in getTransferStatus by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2379
• ci: add manual "Cancel Queued and Running CI" workflow by @ShangmingCai in https://github.com/kvcache-ai/Mooncake/pull/3117
• ci: fix cancel-ci listing that matched no runs by @ShangmingCai in https://github.com/kvcache-ai/Mooncake/pull/3123
• [TENT] Fix req_map_ leak for single-task batches in ascend transport by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/3116
• [PG] Forward collectives through the backend shim for PyTorch 2.13 by @mmangkad in https://github.com/kvcache-ai/Mooncake/pull/3122
• [Store] implement RFC [#2756] batch-record HA OpLog writer by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/2826
• Fix: allocation_strategy not taking effect when enable_ha is enabled on master by @gitgaoqian in https://github.com/kvcache-ai/Mooncake/pull/3077
• [CI] Add nightly build/release and test workflow by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/2950
• [CI] Add staryxchen for Mooncake TE's codeowner by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/3132
• [TransferEngine] Harden socket handshake frame handling by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/3050
• [Bugfix] Fix double free of RDMA slice on device-selection failure by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3125
• [tent] Fix Prometheus histogram silent-drop and clean stale config keys by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/3126
• [PG][2/N] Introduce Control Plane by @caozhanhao in https://github.com/kvcache-ai/Mooncake/pull/2455
• fix(rdma): auto-chunk MRs larger than device max_mr_size (#2017) by @jiejingzhangamd in https://github.com/kvcache-ai/Mooncake/pull/2644
• [P2P-Store] Fix double-close panic, refCount copy, and offset reset by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2375
• [CI/Build] master image: install ibverbs-providers and publish a CUDA 13 flavor by @tpiperatgod in https://github.com/kvcache-ai/Mooncake/pull/3121
• [CI/Build] Remove CUDA dependency from mooncake_master by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3119
• [CI/Build] Add ARM64 Non-CUDA release wheels by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3096
• [Store] Add shared thread-local random helpers by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2954
• [Store] Fix segment capacity metric leak on master service teardown by @liuzijing2014 in https://github.com/kvcache-ai/Mooncake/pull/3154
• [TENT] Harden ShmTransport backing-file and mapping lifecycle by @alexps9 in https://github.com/kvcache-ai/Mooncake/pull/3145
• [Bugfix] Fix double free of UB/Barex slices on device-selection failure by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/3146
• [Store] Surface partial replica allocation in PutStart and document allocation semantics by @liangxu2000 in https://github.com/kvcache-ai/Mooncake/pull/3156
• [Store] Fix SSD total capacity showing incorrectly after master restart by @NUABO in https://github.com/kvcache-ai/Mooncake/pull/3069
• [Store] Fix null-ptr crash in PrepareStorageBackend by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/3138
• [Store] Add dlopen Rust backend and WITH_STORE_C_SHARED shared library by @donghun-furiosa in https://github.com/kvcache-ai/Mooncake/pull/3078
• [Bugfix][Common] Avoid etcd keepalive pings without active streams by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3144
• [TransferEngine] Add NCCL host and device transport backend by @akhillanger in https://github.com/kvcache-ai/Mooncake/pull/2852
• [Store] Make RPC client I/O threads configurable via MC_RPC_CLIENT_IO_THREADS by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3004
• [Misc] Update CODEOWNERS for docs, CI, and HA by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/3175
• [CI/Build] Align Asio with yalantinglibs target by @CanYangGetYang in https://github.com/kvcache-ai/Mooncake/pull/3170
• [tent] Support mixed DRAM+VRAM segments and multi-transport allocation in tebench by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/3127
• [CI] Fix nightly workflow: drop removed build-with-ep input by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/3172
• [TE] fix(efa): bind a CUDA context before registering GPU memory by @whn09 in https://github.com/kvcache-ai/Mooncake/pull/3177
• [Bugfix][TE] Respect remote_accessible in RDMA verbs MR registration by @RuiqingFeng in https://github.com/kvcache-ai/Mooncake/pull/3151
• [Store] Scope capacity metric release to the serving MasterService by @liuzijing2014 in https://github.com/kvcache-ai/Mooncake/pull/3168
• [Store] Fix NoF heartbeat config silently ignored in HA mode by @NUABO in https://github.com/kvcache-ai/Mooncake/pull/3149
• [Doc] Document master KV event publisher flags by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3150
• [Dep] bind wildcard listen address (0.0.0.0/::) without going through getaddrinfo by @pjdurden in https://github.com/kvcache-ai/Mooncake/pull/2919
• [TENT] Fix failover attempt metrics attribution by @anranxia in https://github.com/kvcache-ai/Mooncake/pull/3109
• [CI/Build] Deduplicate EFA and store CI workflows by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3163
• [CI/Build] Format only changed C++ lines by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3027
• [Bugfix][Store] Support JsonCpp header layouts across Linux distributions by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3193
• [Store] support tensor APIs with dummy client by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2998
• [Store] Fix mem storage display showing 16777216 TB when no segment i… by @leonzzhu in https://github.com/kvcache-ai/Mooncake/pull/3080
• [Store] Add Optional Object Checksum Diagnostics by @yokinoshitayoki in https://github.com/kvcache-ai/Mooncake/pull/3003
• [Store] Fix EraseMetadata leaking stale entries in offloading_objects by @huniu20 in https://github.com/kvcache-ai/Mooncake/pull/3160
• [Bugfix][TE] Split RDMA slices at MR boundaries and handle submit errors by @RuiqingFeng in https://github.com/kvcache-ai/Mooncake/pull/3198
• feat(rdma): enable PCI relaxed ordering by default by @1998zxn in https://github.com/kvcache-ai/Mooncake/pull/3205
• [TransferEngine] Reject peer segment descriptors with more keys than devices by @eharris128 in https://github.com/kvcache-ai/Mooncake/pull/3209
• [PG] Fix single-rank initialization and yalantinglibs dependency by @caozhanhao in https://github.com/kvcache-ai/Mooncake/pull/3164
• [CI/Build] Unify CI and release wheel builds by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3137
• [CI] Fix TONE SGLang Qwen3.5 cache gating by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3195
• [Doc] Update RBG integration example to workloads.x-k8s.io/v1alpha2 by @tpiperatgod in https://github.com/kvcache-ai/Mooncake/pull/3224
• Bump google.golang.org/grpc from 1.79.3 to 1.82.1 in /mooncake-common/etcd by @dependabot[bot] in https://github.com/kvcache-ai/Mooncake/pull/3235
• [Store] Add exponential backoff for ordered oplog writer retries by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3166
• [ROCm] Add ROCm/HIP wheel build, CI, and release parity with CUDA (#3171) by @andyluo7 in https://github.com/kvcache-ai/Mooncake/pull/3184
• [Common/TE] Replace hardcoded CUDA paths with CUDAToolkit discovery by @caozhanhao in https://github.com/kvcache-ai/Mooncake/pull/3215
• [TENT] Reject malformed numeric metrics environment overrides by @Hubert-Zhu in https://github.com/kvcache-ai/Mooncake/pull/3228
• [TE] perf(efa): allow bounding the batch MR registration fan-out by @whn09 in https://github.com/kvcache-ai/Mooncake/pull/3210
• [Store] Consolidate string parsing primitives by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3179
• [Bug]: [SSD] DSV4 enable SSD offload，stress testing, repeat offloading the same batch key, lead to OBJECT_ALREADY_EXISTS/persist failed/INVALID_KEY by @pjdurden in https://github.com/kvcache-ai/Mooncake/pull/2967
• [Bugfix] Clear RDMA context health counter only on successful completions by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3230
• [Bugfix] Drain RDMA async event queue on each epoll wakeup by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3236
• [CI] Fix nightly Go path and gate publishing on tests by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3211
• [Store] Fix silent data corruption in io_uring read path (#3066) by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/3073
• [Bugfix] Detect AMD amdgpu for TENT GPUDirect RDMA capability by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/3242
• [Store] Selectively materialize BatchEvict candidates after timestamp filtering by @jacklin78911-collab in https://github.com/kvcache-ai/Mooncake/pull/3118
• [Bugfix] Use GPU_PREFIX for HCA peer affinity under USE_HIP by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/3248
• [CI/Build] Add CUDA 13 EFA wheel by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3247
• [Bugfix][Store] Fix No rkey for MR access on SSD offload read by @NUABO in https://github.com/kvcache-ai/Mooncake/pull/3246
• [CI/Build] Fix nightly workflow and offload platform checks by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3148
• [Store] Validate durable oplog prefix at startup by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3165
• [Bugfix][TE] Fix dma-buf offsets for chunked GPU MRs by @RuiqingFeng in https://github.com/kvcache-ai/Mooncake/pull/3243
• [Store]Support VRAM Segment and NVLink transport within a single node by @zhaoyongke in https://github.com/kvcache-ai/Mooncake/pull/3196
• [CI/Build] Restrict nightly workflow to upstream repository by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3268
• add SUPA (Biren GPU) support to transfer engine by @cyqmonkey in https://github.com/kvcache-ai/Mooncake/pull/3102
• [Bugfix][TE] Keep context_list_ index-aligned when an RNIC fails to init by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3263
• [TE] perf(efa): optionally register device memory only on topology-local NICs by @whn09 in https://github.com/kvcache-ai/Mooncake/pull/3219
• [Store] Fix EFA transport auto-discovery by @yyun-cpu in https://github.com/kvcache-ai/Mooncake/pull/3207
• [Bugfix][TENT] Bound peer key lookups by the published vector length by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3265
• [Store] support CUDA IPC for dummy client buffers by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3234
• [Store] Add Fast-Fail for Impossible OffsetAllocator Requests by @bitborne in https://github.com/kvcache-ai/Mooncake/pull/3222
• Add scatter transfer batching to transfer engine by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3000
• [Store][TE] fabric_mem best-effort alloc via percentile ladder by @ascend-direct-dev in https://github.com/kvcache-ai/Mooncake/pull/3214
• [PG] Decouple PG from PyTorch by @caozhanhao in https://github.com/kvcache-ai/Mooncake/pull/3206
• test: poll for the async eviction in PutStartExpiringTest by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/3266
• [Store] fix: Honor OpLog poll interval command-line override by @00fish0 in https://github.com/kvcache-ai/Mooncake/pull/3255
• [TENT] Retire stale endpoint on peer reconnect bootstrap by @guptaishaan in https://github.com/kvcache-ai/Mooncake/pull/3188
• fix: add CUDA stubs dir to link_directories for no-driver builds by @stmatengss with @Copilot in https://github.com/kvcache-ai/Mooncake/pull/3237
• [Store] Fix processing_keys double-erase UAF in MetadataAccessorRW by @rockuw in https://github.com/kvcache-ai/Mooncake/pull/3254
• [Store] Fix CUDA IPC ranged read build by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3294
• [Misc] Remove unused Python imports and variables from CodeQL findings by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/3260
• Update CODEOWNERS to include zxpdemonio by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/3288
• fix(transfer-engine): block SIGTERM/SIGINT for the shutdown watcher by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/3278
• [Wheel] Add native fast-copy PUT hot path by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3112
• [EP] Add EP dispatch/combine benchmark with incast routing patterns by @PACTHEMAN123 in https://github.com/kvcache-ai/Mooncake/pull/3213
• [Doc] Add Biren logo to supported hardware by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3298
• [TENT] cuda_probe: zero-init cudaPointerAttributes and warn on libcud… by @KubrickLiu in https://github.com/kvcache-ai/Mooncake/pull/3261
• fix(musa): add missing CUDA compatibility macros by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3295
• [TENT] RDMA: skip NICs that cannot GPUDirect-DMA to a GPU, and fix fallback device rotation by @anranxia in https://github.com/kvcache-ai/Mooncake/pull/3281
• [TE] EFA: derive WR/CQ pacing depths from the libfabric provider by @whn09 in https://github.com/kvcache-ai/Mooncake/pull/3296
• [Bugfix][TENT] Keep context_set_ and buffer keys NicID-indexed by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3264
• [Store] Add minimal MasterService scenario DSL by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3256
• [TENT] Fix double-free in HttpMetaStore under concurrent workers: a s… by @KubrickLiu in https://github.com/kvcache-ai/Mooncake/pull/3259
• [CI/Build] Simplify wheel workflows by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3283
• [PG] Build the device worker with C++17 for CMake 3.22 compatibility by @caozhanhao in https://github.com/kvcache-ai/Mooncake/pull/3308
• [TransferEngine] Make single unregisterLocalMemory best-effort by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2962
• [TransferEngine] Skip the CUDA pointer probe on GPU-less hosts by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/2955
• fix: resolve nightly CI failures by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3309
• [TE] Support DMA-BUF in IBGDA Device API by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3272
• [TENT] Add native UB foundation and URMA resource management by @zchuango in https://github.com/kvcache-ai/Mooncake/pull/3282
• [CI] Disable Qoder auto code review workflow by @stmatengss with @Copilot in https://github.com/kvcache-ai/Mooncake/pull/3306
• [Bugfix][TE] Serialize libnuma's lazy cpumask cache fill in bindToSocket by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3289
• [Store] Harden Put/Upsert completion against promotion lifecycle by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/3244
• [CI] synchronize metadata server handoff by @zhangzuo21 in https://github.com/kvcache-ai/Mooncake/pull/3212
• [Docs][Store] document task manager replica task behavior by @stmatengss with @Copilot in https://github.com/kvcache-ai/Mooncake/pull/3300
• [Store] Fix stale per-segment metric labels after segment unmount by @leonzzhu in https://github.com/kvcache-ai/Mooncake/pull/3301
• [TE] Fix compiler warnings in IBGDA transport by @leonzzhu in https://github.com/kvcache-ai/Mooncake/pull/3312
• [Wheel] Support jagged NestedTensor transfer by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3336
• [PG] Support inplace rejoin and fix p2p recovery by @caozhanhao in https://github.com/kvcache-ai/Mooncake/pull/3323
• [Wheel] Optimize typed-ragged rollout layout by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3113
• [Bugfix] clean up partially initialized TENT RDMA contexts by @runzhech in https://github.com/kvcache-ai/Mooncake/pull/3325
• [Bugfix][TENT] Keep a never-constructed context in the NicID slot by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3339
• [Store] Support pinned SSD-to-GPU restore by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3319
• [Store] Fix flaky standby catch-up test by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3273
• [TE] Support split IBGDA control memory for MUSA by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3334
• [Store] Remove dead DRAM/NoF metric overload declarations by @Hubert-Zhu in https://github.com/kvcache-ai/Mooncake/pull/3344
• [Store] Remove transient MasterService config fields by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3313
• [Store] Extend MasterScenario DSL for upsert lifecycle by @bitborne in https://github.com/kvcache-ai/Mooncake/pull/3328
• [Wheel] Add DataProto catalog for fragmented rollout data by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3345
• [Store] Add put/get session APIs for ranged multi-buffer transfers by @ascend-direct-dev in https://github.com/kvcache-ai/Mooncake/pull/2881
• Support custom SSH ports in SPDK target creation by @stmatengss with @Copilot in https://github.com/kvcache-ai/Mooncake/pull/3307
• [Doc] Update Mooncake PG design documentation by @caozhanhao in https://github.com/kvcache-ai/Mooncake/pull/3353
• [Doc] Update PyPI package documentation by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3356
• Allow configuring master admin/metrics HTTP bind address by @nogumanov in https://github.com/kvcache-ai/Mooncake/pull/3318
• [CI/Build] Fix nightly CUDA stub runtime by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3346
• [Transfer Engine] Schedule TCP transfers on bounded per-peer connection lanes by @jacklin78911-collab in https://github.com/kvcache-ai/Mooncake/pull/2974
• [Doc] Align Python setup API documentation by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3357
• [CI/Build] Isolate nightly Python tests in venv by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3373
• [Store] Add batch OpLog snapshot metadata protocol by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3178
• [Store] Add producer view to durable oplog prefix by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3201
• [Store] Add fixed soft pin lifecycle by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/2909
• [Bugfix] use BufferPool for zcopy benchmark by @030611 in https://github.com/kvcache-ai/Mooncake/pull/3342
• [Store] Avoid staging for same-process GPU reads by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3197
• [Store] Add deterministic MasterScenario object lifecycle coverage by @bitborne in https://github.com/kvcache-ai/Mooncake/pull/3368
• [TransferEngine] Fix graceful shutdown test hangs in USE_ETCD builds by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3351
• [Store] Fix race in HA durable-finalization tests (#3332) by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3333
• feat(ascend_direct): auto-detect AutoConnect & Client-Server mode via GetCapability, inject LocalCommRes by @JieTang66 in https://github.com/kvcache-ai/Mooncake/pull/3302
• [Doc] Add Multi-tenant Deployment Guide by @yokinoshitayoki in https://github.com/kvcache-ai/Mooncake/pull/3378
• [Doc] Align pre-commit guidance to PR-changed files by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/3277
• [Bugfix][TE] Reject MC_IB_PORT=0 instead of disabling every RNIC by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3381
• [Store] Fix current-stream readiness for DummyClient CUDA IPC tensor writes by @mo-ke-ke in https://github.com/kvcache-ai/Mooncake/pull/3303
• [Store] Support configurable fileread worker pool size by @NUABO in https://github.com/kvcache-ai/Mooncake/pull/3348
• [Bugfix][TE] Install shutdown handlers before unblocking signals by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3390
• [Store] Verify supervisor view propagation by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3352
• [TENT] drain control callbacks on unregister by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3370
• [TransferEngine] Add instant bandwidth reporting to tebench by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/3358
• [Bugfix][Store] Update bucket timestamp after offload to avoid immedi… by @mjwtom in https://github.com/kvcache-ai/Mooncake/pull/3101
• [Store] Add deterministic MasterService eviction scenarios by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3327
• [Store] Make tenant quota charge and release lock-free by @Lin-z-w in https://github.com/kvcache-ai/Mooncake/pull/3162
• [Store] Add DFS replica support with POSIX backend by @fcczzz in https://github.com/kvcache-ai/Mooncake/pull/2683
• [TENT] Port GDS and Ascend transport reliability updates by @Primary33 in https://github.com/kvcache-ai/Mooncake/pull/3280
• [Docs] Reorganize design docs and move tebench to performance by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/3376
• [EP] decouple native EP from torch C++ APIs by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/2883
• [Store] Add terminal state for ordered oplog writer failures by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3204
• [CI] Adjust build concurrency in build-musa workflow by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3415
• [CI/Build] Prevent fixed-port collisions in nightly tests by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3403
• [EP] Fix incorrect target name under condition EP_USE_IDE by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3418
• [TransferEngine] Share one host KV segment across a TP group by @ascend-direct-dev in https://github.com/kvcache-ai/Mooncake/pull/3285
• [Reshard] Add resource and model-weight manifest contracts by @Bo-Vincent in https://github.com/kvcache-ai/Mooncake/pull/3187
• [Store] Defer invalid handle cleanup from segment unmount RPC by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/2877
• [store] Avoid staging copy for same node tensor put by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3159
• [TE] Add RDMA ctrl frame codec and sender credit ledger by @zhtshr in https://github.com/kvcache-ai/Mooncake/pull/3324
• [Bug]: RDMA reconnect storm after mlx5 local length errors by @pjdurden in https://github.com/kvcache-ai/Mooncake/pull/3387
• [Bugfix][TENT] Lock ProxyManager's stage buffer map by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3410
• MPComm Transport for TENT — an RDMA-native multi-rail transport backend by @c-guo16 in https://github.com/kvcache-ai/Mooncake/pull/3423
• [Build] Stage native _ep extension into ep_pg_staging for wheel packaging by @JunlinW113 in https://github.com/kvcache-ai/Mooncake/pull/3432
• [ci] enable ARM64 Mooncake EP build by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3442
• [Store] Fix NoF benchmark build: gflags flags inside anonymous namespace by @NUABO in https://github.com/kvcache-ai/Mooncake/pull/3420
• [Bugfix][Store] Keep snapshot unmount test on the synchronous cleanup path by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3429
• [Doc] Updating maintainers document with new logs by @stmatengss with @Copilot in https://github.com/kvcache-ai/Mooncake/pull/3430
• [Store] Add object storage adapter abstraction by @fcczzz in https://github.com/kvcache-ai/Mooncake/pull/3043
• [Bugfix][Store] Release allocator gaps after snapshot recovery by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3414
• [Bugfix][Store] Avoid futile PutStart eviction triggers by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3419
• [Store] introduce NVMe KV backend core by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/2167
• [Store] Fix: preempt in-progress offload task on UpsertStart by @huniu20 in https://github.com/kvcache-ai/Mooncake/pull/3253
• [TENT] Support custom NIC priority matrix and native topology dump by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/3382
• [Bugfix][TENT] Pace the transfer poll loops and stop leaking their batches by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3407
• [CI/Build] Install patchelf from PyPI for auditwheel repair by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3458
• [Transfer Engine] Optimize scatter transfer with grouped tasks by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3310
• [TENT] Make ProxyManager staging cleanup safe and asynchronous by @RuiqingFeng in https://github.com/kvcache-ai/Mooncake/pull/3380
• [BugFix][TENT] Fix race condition in DispatchesOnlyOneWindowOnSubmit test by @RuiqingFeng in https://github.com/kvcache-ai/Mooncake/pull/3460
• [Bugfix][Store] Fix hybrid histogram serialization by @JimmyWang0417 in https://github.com/kvcache-ai/Mooncake/pull/3456
• [Bugfix][TENT] Keep a delegated transfer off the RPC event loop by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3404
• [TE] Skip same-host device offset when HIXL CS mode is available by @jinsidong in https://github.com/kvcache-ai/Mooncake/pull/3453
• [Store] Return explicit standby restore errors by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3354
• [Bugfix][Store] Preserve RequiredParam names when copied by @JimmyWang0417 in https://github.com/kvcache-ai/Mooncake/pull/3457
• [Store] Add dynamic hot replica fanout by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3389
• feat(cuda): add sm103 to CUDA 13 builds by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3444
• [CI] Move PR build validation to nightly by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3482
• [CI] Simplify build-flags by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3485
• [CI] avoid pinning torch version to 2.11.0 by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3469
• [TENT] Resolve transport policy device masks once, not per request by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3490
• [TENT] reclaim rdma endpoints outside store lock by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3369
• TENT: link tent_runtime against mooncake_common by @xiaodouzi666 in https://github.com/kvcache-ai/Mooncake/pull/3405
• TENT: only deliver transfer-bound notifications after completion by @xiaodouzi666 in https://github.com/kvcache-ai/Mooncake/pull/3406
• [TransferEngine] Add MUSA IPC transport with batched copies by @yeahdongcn in https://github.com/kvcache-ai/Mooncake/pull/3035
• [TransferEngine] Bind buffer device for EFA CUDA loopback by @yejun-yun in https://github.com/kvcache-ai/Mooncake/pull/3436
• [Store] Stabilize snapshot PutStart eviction test by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3480
• [Store] Structure OffsetAllocatorBackendConfig environment settings by @bitborne in https://github.com/kvcache-ai/Mooncake/pull/3408
• [Store] Extract LocalSSD management from SegmentManager by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3427
• [Bugfix][Store] Fix MoveEnd source refcnt leak on target gone by @lxy-alexander in https://github.com/kvcache-ai/Mooncake/pull/3443
• [CI][Store] Fix promotion-on-hit e2e flakiness from cross-class segment leaks by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/3466
• [Store] Bucket: add MAX_PHYSICAL_BYTES cap on real shared-disk usage by @Morpheus799 in https://github.com/kvcache-ai/Mooncake/pull/3467
• [Bugfix][Store] Protect unreadable recovered replicas from eviction by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3421
• [Store]: Split segments by transport limit by @yokinoshitayoki in https://github.com/kvcache-ai/Mooncake/pull/3486
• [Store] Fence batch oplog writers by producer view by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3384
• [TransferEngine] Support multi-target tebench runs by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3391
• [Store] Add bounded standby snapshot capture by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3326
• [TransferEngine] Split EFA transfers that straddle BufferDesc chunk boundaries by @whn09 in https://github.com/kvcache-ai/Mooncake/pull/3505
• [Docs][TENT] Document the FakeTransport runtime test mechanism by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/3489
• [Bugfix][Store] Fix standby snapshot compile regressions by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3515
• [Store] Clean up behavior-focused tests by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3495
• [CI/Build] Make CMake target dependencies explicit by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3276
• fix(store): deduplicate SSD carryover keys by @982945902 in https://github.com/kvcache-ai/Mooncake/pull/3479
• [Store][TE] Split Ascend agent-mode store pool across n engines by @ascend-direct-dev in https://github.com/kvcache-ai/Mooncake/pull/3450
• [Bugfix][TE] Log the RDMA port number as an integer, not a byte by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3512
• [TENT] Make RPC server thread count configurable via MC_TENT_RPC_THREADS by @gogongxt in https://github.com/kvcache-ai/Mooncake/pull/3535
• [TENT] Reduce copies in the TCP data path (sendData/onRecvData) by @gogongxt in https://github.com/kvcache-ai/Mooncake/pull/3536
• [TE] Rename create_shared_segment tp_group to comm_group by @ascend-direct-dev in https://github.com/kvcache-ai/Mooncake/pull/3481
• [Bugfix][Store] Fix partial-unmount snapshot test race by @thunguo in https://github.com/kvcache-ai/Mooncake/pull/3549
• [transfer-engine] Ship intra-node NVLink transport in x86_64 CUDA wheels by @ShangmingCai in https://github.com/kvcache-ai/Mooncake/pull/3547
• [Other] Add Aionw as codeowner for Store HA by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/3524
• [Reshard] Add N-D logical weight transfer planner by @Bo-Vincent in https://github.com/kvcache-ai/Mooncake/pull/3441
• [Store] Give LOCAL_DISK segments an unmount half, and let the offload RPC honour connect timeouts by @Juhyun-Kim-Memphis in https://github.com/kvcache-ai/Mooncake/pull/3316
• [Store] Add chunked standby snapshot artifact writer by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3447
• fix(store): reject cross-shard duplicates during standby restore by @982945902 in https://github.com/kvcache-ai/Mooncake/pull/3527
• [Store] Skip full metadata scan in ReMountSegment when unneeded (#3517) by @KubrickLiu in https://github.com/kvcache-ai/Mooncake/pull/3533
• perf(store): batch io_uring bucket reads by @982945902 in https://github.com/kvcache-ai/Mooncake/pull/3488
• [wheel] preserve grouped writes for structured objects by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3133
• [CI/Build] Fix Ascend master linkage by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3565
• [Build] Establish scikit-build-core Python project foundation by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3577
• [TE] Enhance Transfer Engine Rust library with CI tests and fixes by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/3461
• [TE] Expand config env-var test coverage by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/2409
• [Docs] Update News by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/3580
• [TE] Add rdma_twosided control-plane notify channel by @zhtshr in https://github.com/kvcache-ai/Mooncake/pull/3440
• [Bugfix][Store] Allow HA promotion without OpLog by @Icedcoco in https://github.com/kvcache-ai/Mooncake/pull/3566
• [Bugfix][TENT] Unpin remote stage buffers after late completion by @RuiqingFeng in https://github.com/kvcache-ai/Mooncake/pull/3494
• [Store] Structure FileStorageConfig environment settings by @bitborne in https://github.com/kvcache-ai/Mooncake/pull/3525
• [CI] Install sgl-eval for T-One SGLang tests by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3605
• [TransferEngine] Add a TCP session progress deadline by @jacklin78911-collab in https://github.com/kvcache-ai/Mooncake/pull/3542
• [TransferEngine] Enable TCP connection pool by default by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/3569
• [TENT] fix: synchronize with caller's per-thread stream before issuing NVLink/MNNVL batched copy by @TTThanos in https://github.com/kvcache-ai/Mooncake/pull/3570
• [Bugfix][TENT] Keep lazyFreeBatch sweeping past a batch it cannot reclaim by @SongOf in https://github.com/kvcache-ai/Mooncake/pull/3514
• [CI/Build] Header only YLT (yalantinglibs) by @ur4t in https://github.com/kvcache-ai/Mooncake/pull/3537
• [Store] Fix promotion-on-hit delivery starvation and retry loss by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/3545
• [TransferEngine] Fix duplicate cleanup in transport tests by @ASCII-S in https://github.com/kvcache-ai/Mooncake/pull/3583
• [Docs] Add UCL-MPComm to the Updates list in README, and measured performance data in docs. by @c-guo16 in https://github.com/kvcache-ai/Mooncake/pull/3621
• [CI] Add Reshard module test gate by @Bo-Vincent in https://github.com/kvcache-ai/Mooncake/pull/3622
• Bump version to 0.3.13 in pyproject.toml by @ShangmingCai in https://github.com/kvcache-ai/Mooncake/pull/3597
• [TransferEngine] Add FlagCX support by @MC952-arch in https://github.com/kvcache-ai/Mooncake/pull/3522
• [TENT] Bound the pending-batch drain wait in ProxyManager shutdown by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/3526
• [CI/Build] Preserve CTest failure diagnostics by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3445
• [Store] Decouple business decisions from storage metrics by @Hubert-Zhu in https://github.com/kvcache-ai/Mooncake/pull/3385
• [TENT] Canonicalize AMD GPU location prefix to hip: (keep rocm: as parse alias) by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/3532
• [Store] Establish typed MasterService test DSL by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3510
• [TransferEngine] Fix TCP endpoint refresh correctness by @jacklin78911-collab in https://github.com/kvcache-ai/Mooncake/pull/3543
• [Store] Shrink metadata maps after eviction cycles by @jfeng18 in https://github.com/kvcache-ai/Mooncake/pull/3576
• [Store] Avoid direct-I/O padding for POSIX restores by @zupengwang in https://github.com/kvcache-ai/Mooncake/pull/3606
• [Bugfix][TENT] Fix RailMonitor topology use-after-free by @lxy-alexander in https://github.com/kvcache-ai/Mooncake/pull/3598
• [Wheel] Add DataProto catalog lifecycle management by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/3374
• fix(ep,pg): prevent cudaErrorIllegalAddress during CUDA graph capture with TBO by @UNIDY2002 in https://github.com/kvcache-ai/Mooncake/pull/3609
• [Bugfix] Isolate Mooncake Store test data directories by @fcczzz in https://github.com/kvcache-ai/Mooncake/pull/3650
• [TransferEngine] Link gcov runtime for Rust coverage builds by @alogfans in https://github.com/kvcache-ai/Mooncake/pull/3612
• [MUSA] Backport YLT include propagation to v0.3.13 by @Aionw in https://github.com/kvcache-ai/Mooncake/pull/3694

New Contributors

• @JieTang66 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2178
• @fcczzz made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2209
• @Dao007forever made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2148
• @leonzzhu made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2144
• @muma378 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2227
• @CAICAIIs made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2180
• @Enigmo-x made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2172
• @Chelseatr made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2222
• @mmangkad made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2255
• @yuhuiaws made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2113
• @andyluo7 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2225
• @Oxygen56 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2278
• @gogongxt made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2308
• @jfeng18 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2332
• @JimyMa made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2356
• @HubertZhang made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2342
• @zbchi made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2341
• @QAQYangT-T made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2434
• @bp-cheng made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2433
• @feichai0017 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2466
• @huojianqiangg made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2495
• @bitborne made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2508
• @Icedcoco made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2383
• @silas-scitix made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2484
• @HGinkgo made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2340
• @carlushuang made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2566
• @zjjf made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2567
• @catyans made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2526
• @VectorPeak made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2587
• @leveretconey made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2553
• @dadadada-147 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2569
• @zackyoray made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2623
• @mgoin made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2605
• @Makzert made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2539
• @greatwhole made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2557
• @hzt123123 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2616
• @wqwqazwsxedc made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2535
• @c-guo16 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2696
• @ZhijunLStudio made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2698
• @tpiperatgod made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2678
• @xiangui33423 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2691
• @Liwink made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2733
• @smartssw made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2685
• @n-WN made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2741
• @mikegguo made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2417
• @jacklin78911-collab made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2584
• @SuperMarioYL made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2456
• @Csrayz made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2803
• @morluto made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2891
• @tong1heng made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2921
• @chethanuk made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2968
• @anranxia made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2978
• @Srinivasoo7 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2690
• @HeinUmin made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2996
• @liangxu2000 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2944
• @RuiqingFeng made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3020
• @g122622 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3022
• @gitgaoqian made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3077
• @SongOf made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3125
• @jiejingzhangamd made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2644
• @liuzijing2014 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3154
• @alexps9 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3145
• @akhillanger made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2852
• @CanYangGetYang made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3170
• @pjdurden made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/2919
• @huniu20 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3160
• @eharris128 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3209
• @Hubert-Zhu made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3228
• @cyqmonkey made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3102
• @yyun-cpu made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3207
• @guptaishaan made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3188
• @rockuw made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3254
• @PACTHEMAN123 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3213
• @KubrickLiu made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3261
• @runzhech made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3325
• @nogumanov made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3318
• @030611 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3342
• @mo-ke-ke made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3303
• @mjwtom made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3101
• @zhtshr made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3324
• @JimmyWang0417 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3456
• @jinsidong made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3453
• @xiaodouzi666 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3405
• @yejun-yun made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3436
• @lxy-alexander made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3443
• @Morpheus799 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3467
• @982945902 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3479
• @thunguo made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3549
• @Juhyun-Kim-Memphis made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3316
• @ur4t made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3537
• @ASCII-S made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3583
• @zupengwang made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/3606

Full Changelog: https://github.com/kvcache-ai/Mooncake/compare/v0.3.11...v0.3.13