Mooncake Files

What's Changed

• [Store] support resolving master RPC address from interface by @YiXR in https://github.com/kvcache-ai/Mooncake/pull/1784
• Bump google.golang.org/grpc from 1.59.0 to 1.79.3 in /mooncake-common/etcd by @dependabot[bot] in https://github.com/kvcache-ai/Mooncake/pull/1785
• [Transfer Engine] Round-robin slice batch across QPs in RdmaEndPoint::submitPostSend by @usernamehaha2022 in https://github.com/kvcache-ai/Mooncake/pull/1721
• [CI] Optimize CI/CD workflow execution order to implement a fail-fast mechanism by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/1782
• [STORE] split HA runtime and unify standby lifecycle by @YiXR in https://github.com/kvcache-ai/Mooncake/pull/1777
• [Build] add yalantinglibs submodule by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/1781
• [Store] Add C API for Mooncake Store by @jiangyukunok in https://github.com/kvcache-ai/Mooncake/pull/1763
• [P2P] fix: cannot disable NV_PEERMEM and enable CUDA at the same time by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/1797
• [Bugfix][Build] Fix S3SnapshotObjectStore Pimpl error & improve build reliability by @timzhang0727 in https://github.com/kvcache-ai/Mooncake/pull/1796
• fix: fix eviction notification unit test to ensure deterministic FIFO order by @00fish0 in https://github.com/kvcache-ai/Mooncake/pull/1800
• [TENT] Fix duplicate notify recv WR posting and PLOG misuse in RDMA endpoint by @dtcccc in https://github.com/kvcache-ai/Mooncake/pull/1803
• [CI] fix bugs with CI pr1782: fail-fast on format check and restore Ascend/Integration as PR gates by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/1806
• [Store] Add Upsert API for in-place object updates by @00fish0 in https://github.com/kvcache-ai/Mooncake/pull/1662
• [TENT] Disconnect before registering memory by @Cheng-China in https://github.com/kvcache-ai/Mooncake/pull/1807
• Update codeowners by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/1819
• [Store] Add Go language bindings for Mooncake Store by @jiangyukunok in https://github.com/kvcache-ai/Mooncake/pull/1764
• [Misc] Fix silent failure in code_format.sh when clang-format is missing by @caozhanhao in https://github.com/kvcache-ai/Mooncake/pull/1824
• [PG] Implement graceful shutdown and reland CPU-only tests to CI by @caozhanhao in https://github.com/kvcache-ai/Mooncake/pull/1795
• [PG]: fix barrier imple problem by @KMSorSMS in https://github.com/kvcache-ai/Mooncake/pull/1792
• [TE] Enabling UB Transport on the Kunpeng SuperNode Phase 1 by @zchuango in https://github.com/kvcache-ai/Mooncake/pull/1805
• [PG] Introduce comprehensive test suite by @yuechen-sys in https://github.com/kvcache-ai/Mooncake/pull/1790
• [STORE] tighten snapshot correctness and reload snapshot-only standby from catalog by @YiXR in https://github.com/kvcache-ai/Mooncake/pull/1801
• Add native Rust bindings for Mooncake Store with usage example and CI integration by @Copilot in https://github.com/kvcache-ai/Mooncake/pull/1810
• [TENT] Fix NVLink IPC address for sub-allocated GPU tensors by @he-yufeng in https://github.com/kvcache-ai/Mooncake/pull/1831
• [PG][TE][TENT] Add dedicated peer liveness probe for recovery and enable elastic GPU test by @KMSorSMS in https://github.com/kvcache-ai/Mooncake/pull/1808
• [TE] feat: setup the RDMA for mlu device. by @phantomlei3 in https://github.com/kvcache-ai/Mooncake/pull/1799
• Optimize ci fail-fast scheme by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/1813
• fix: increase ParallelAllocation test pool to 32MB to avoid flaky slab race by @00fish0 in https://github.com/kvcache-ai/Mooncake/pull/1841
• [Bug fix] Fix get tcp port collision by @zhangzuo21 in https://github.com/kvcache-ai/Mooncake/pull/1816
• [TENT] Register base address of a buffer instead of its sub-allocated address into BufferDesc by @shuoerw in https://github.com/kvcache-ai/Mooncake/pull/1837
• [TE] Add Multi-Protocol Support for DRAM-CXL-SSD tiered storage by @hemist in https://github.com/kvcache-ai/Mooncake/pull/1832
• [TENT] Fix stale segment cache via withCachedSegment and async invalidation by @caozhanhao in https://github.com/kvcache-ai/Mooncake/pull/1826
• [Store] Introduce HA OpLog abstraction and LocalFS oplog store by @duhaode520 in https://github.com/kvcache-ai/Mooncake/pull/1804
• [TRANSFER_ENGINE] align USE_MACA with MUSA GPU paths and docs by @Dayuxiaoshui in https://github.com/kvcache-ai/Mooncake/pull/1814
• feat(store): expose drain job control via master HTTP API by @XucSh in https://github.com/kvcache-ai/Mooncake/pull/1815
• [TENT] Fix potential deadlock and UAF in synchronizeLocal in [#1826] by @caozhanhao in https://github.com/kvcache-ai/Mooncake/pull/1849
• fix(docker): respect PYTHON_VERSION build-arg when building wheel by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/1745
• [CI] Harden CI pipeline: path filtering, concurrency, on-demand E2E, and security fixes by @00fish0 in https://github.com/kvcache-ai/Mooncake/pull/1846
• [store] Add get_into_ranges to support Grouped Scatter RDMA Reads by @zxpdemonio in https://github.com/kvcache-ai/Mooncake/pull/1717
• [CI] fix: slash command /run-e2e-ci fails for fork PRs by @00fish0 in https://github.com/kvcache-ai/Mooncake/pull/1859
• [Store] Fix with_hard_pin failure in python API by @0oshowero0 in https://github.com/kvcache-ai/Mooncake/pull/1873
• [Bug fix] Prevent redundant replica pinning during offloading by @ertcmm in https://github.com/kvcache-ai/Mooncake/pull/1853
• [TransferEngine] Add retry, async execution, and graceful shutdown for TENT TCP transport by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/1866
• [TransferEngine][ROCm] Add ROCm HIP support to the Mooncake Python package by @knitcapcat-amd in https://github.com/kvcache-ai/Mooncake/pull/1742
• [Docs] Add SSD offload benchmark results by @zhangzuo21 in https://github.com/kvcache-ai/Mooncake/pull/1835
• [Store] Support SSD offload via Python setup() interface by @zhangzuo21 in https://github.com/kvcache-ai/Mooncake/pull/1857
• [MISC] Add CODEOWNERS for efa_transport directory by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/1885
• [TE] Enabling UB Transport on the Kunpeng SuperNode Phase 2 by @zchuango in https://github.com/kvcache-ai/Mooncake/pull/1855
• [TransferEngine][MACA] Align MACA build paths with CMake options by @Dayuxiaoshui in https://github.com/kvcache-ai/Mooncake/pull/1888
• [TENT] Wire up cross-transport failover with safety limits and observability by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/1878
• [TENT] Enhance memory registration with transport type support by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/1877
• [Store] Support SSD Metrics by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/1879
• [TENT] Fix crashes caused by negative numa_node and incorrect config type inference by @dtcccc in https://github.com/kvcache-ai/Mooncake/pull/1894
• [Store] Enable NUMA-segmented allocation for RDMA RealClient-only mode by @00fish0 in https://github.com/kvcache-ai/Mooncake/pull/1838
• [CI] fix: health_check_test flaky due to fixed sleep, use polling for master down detection by @herbertskyper in https://github.com/kvcache-ai/Mooncake/pull/1868
• [CI] add configurable GitHub mirror fallback for Ascend checkout by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/1896
• feat(tent): replace raw RdmaEndPoint* with weak_ptr for endpoint lifecycle safety by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/1897
• [Store] Fix hardcoded 127.0.0.1 bind address in standalone client RPC… by @zhangzuo21 in https://github.com/kvcache-ai/Mooncake/pull/1900
• [TENT] Fix static library link group for final targets and reformat related CMake files by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/1893
• [PG][TENT] Fix CUDA collective wait semantics and NVLink small-transfer completion by @KMSorSMS in https://github.com/kvcache-ai/Mooncake/pull/1863
• [Doc] Update Client Explanation by @ykwd in https://github.com/kvcache-ai/Mooncake/pull/1905
• [TE] Add fi_read support, endpoint LRU eviction, and multi-NIC striping for EFA transport by @whn09 in https://github.com/kvcache-ai/Mooncake/pull/1821
• [Store] Enabling setting SSD offload path using python interface by @zhangzuo21 in https://github.com/kvcache-ai/Mooncake/pull/1884
• [Store] Expose batch_replica_clear in Python binding by @hnts03-moreh in https://github.com/kvcache-ai/Mooncake/pull/1848
• [CI] add format hook by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/1904
• [TENT] Batch transfer requests using cudaMemcpyBatchAsync by @shuoerw in https://github.com/kvcache-ai/Mooncake/pull/1890
• Minor bug fixes and improvments for Mooncake Store and Transfer Engine by @nickyc975 in https://github.com/kvcache-ai/Mooncake/pull/1895
• [Store] Fix segfault in disk-replica/offload paths when handling GPU VRAM pointers by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/1892
• fix(ci): retry ascend submodule update via GitHub mirrors by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/1924
• [TENT] add FaultProxyTransport for fault injection testing by @staryxchen in https://github.com/kvcache-ai/Mooncake/pull/1907
• [TE] PTE-aware auto-split large MR registration for EFA transport by @whn09 in https://github.com/kvcache-ai/Mooncake/pull/1912
• [Store] Add client bandwidth metrics for real and dummy clients by @stmatengss in https://github.com/kvcache-ai/Mooncake/pull/1874
• [store] Bug Fix: Local Disk Replica Metadata Not Cleaned Up After Store Node Offline by @Colors-111 in https://github.com/kvcache-ai/Mooncake/pull/1914
• [Store] unify file storage backend env vars under MOONCAKE_OFFLOAD_ p… by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/1929
• [Integration] connector_v1: subclass SupportsHMA so PD-disagg works for hybrid models by @HarshavardhanK in https://github.com/kvcache-ai/Mooncake/pull/1931
• [Store] auto-enable MC_STORE_MEMCPY in TCP-only environments by @dtcccc in https://github.com/kvcache-ai/Mooncake/pull/1936
• [TE] Fix a 1-second stall in RDMA WorkerPool due to store-buffer reordering by @chestnut-Q in https://github.com/kvcache-ai/Mooncake/pull/1932
• [CI] Restore auto-triggered ascend-test and integration-test in ci.yml by @LujhCoconut in https://github.com/kvcache-ai/Mooncake/pull/1943
• [PG] Fix wait() hang during CUDA Graph capture by @caozhanhao in https://github.com/kvcache-ai/Mooncake/pull/1933
• [Store]: Wait for all tasks to complete before completing a batch by @nickyc975 in https://github.com/kvcache-ai/Mooncake/pull/1906
• Pin a patched Go toolchain and track etcd go.sum for wrapper builds by @Copilot in https://github.com/kvcache-ai/Mooncake/pull/1937
• Refactor ASIO shared target into mooncake-common by @Copilot in https://github.com/kvcache-ai/Mooncake/pull/1926
• Bump version to 0.3.10.post2 in pyproject.toml by @ShangmingCai in https://github.com/kvcache-ai/Mooncake/pull/1949

New Contributors

• @usernamehaha2022 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/1721
• @jiangyukunok made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/1763
• @timzhang0727 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/1796
• @zchuango made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/1805
• @phantomlei3 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/1799
• @shuoerw made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/1837
• @0oshowero0 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/1873
• @ertcmm made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/1853
• @knitcapcat-amd made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/1742
• @herbertskyper made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/1868
• @hnts03-moreh made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/1848
• @Colors-111 made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/1914
• @HarshavardhanK made their first contribution in https://github.com/kvcache-ai/Mooncake/pull/1931

Full Changelog: https://github.com/kvcache-ai/Mooncake/compare/v0.3.10.post1...v0.3.10.post2