| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| lmcache-0.3.8-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl | 2025-10-21 | 3.9 MB | |
| lmcache-0.3.8-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl | 2025-10-21 | 3.9 MB | |
| lmcache-0.3.8-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl | 2025-10-21 | 3.9 MB | |
| lmcache-0.3.8-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl | 2025-10-21 | 3.9 MB | |
| lmcache-0.3.8.tar.gz | 2025-10-21 | 1.1 MB | |
| README.md | 2025-10-20 | 7.3 kB | |
| v0.3.8 source code.tar.gz | 2025-10-20 | 1.1 MB | |
| v0.3.8 source code.zip | 2025-10-20 | 1.3 MB | |
| Totals: 8 Items | 19.0 MB | 0 | |
LMCache v0.3.8 should be fully compatible with vLLM v0.11.0
What's Changed
- [minor fix]fix pin_count type by @chunxiaozheng in https://github.com/LMCache/LMCache/pull/1685
- [Docs] Add minimal runnable quick start guide by @kobe0938 in https://github.com/LMCache/LMCache/pull/1725
- [Benchmark] Emphasize query round results in long_doc_qa by @kobe0938 in https://github.com/LMCache/LMCache/pull/1730
- [Core] Remove
lookup_idand usereq_idinstead by @YaoJiayi in https://github.com/LMCache/LMCache/pull/1729 - [minor fix] use parent init to init meta by @chunxiaozheng in https://github.com/LMCache/LMCache/pull/1716
- [Core][RemoteBackend] Implement remove api for remote backend and fs_connector as first step by @maobaolong in https://github.com/LMCache/LMCache/pull/1696
- [Core] Add async Redis cluster connector + unit tests by @lindseywn in https://github.com/LMCache/LMCache/pull/1638
- Bump docker/login-action from 3.5.0 to 3.6.0 by @dependabot[bot] in https://github.com/LMCache/LMCache/pull/1723
- [CI][BugFix]: Enable non-CUDA unit testing for all tests by @hickeyma in https://github.com/LMCache/LMCache/pull/1677
- [Feat] Generate random instance id when the instance id is not defined by @zerofishnoodles in https://github.com/LMCache/LMCache/pull/1734
- [Docs] P2P KV Cache Sharing by @kobe0938 in https://github.com/LMCache/LMCache/pull/1735
- [Docs] Add RunLLM by @kobe0938 in https://github.com/LMCache/LMCache/pull/1736
- [Misc]: Improve the description provided for PRs by @hickeyma in https://github.com/LMCache/LMCache/pull/1679
- [core]Add cache/clear api to internal_api_server by @maobaolong in https://github.com/LMCache/LMCache/pull/1711
- Support remove around quotes in env config by @maobaolong in https://github.com/LMCache/LMCache/pull/1671
- Small fixes to getting_started.md by @SuperGoodGame in https://github.com/LMCache/LMCache/pull/1737
- [Doc] Fix raw-html syntax in index.rst by @Siddhant-Ray in https://github.com/LMCache/LMCache/pull/1738
- [Benchmark] Make long_doc_qa_recommender more user friendly by @kobe0938 in https://github.com/LMCache/LMCache/pull/1731
- [CI/Build] Add async to comprehensive tests by @Shaoting-Feng in https://github.com/LMCache/LMCache/pull/1744
- Fix bug in nixl_channel.py where incorrect variables were used when cleaning up NIXL resources by @xleoken in https://github.com/LMCache/LMCache/pull/1630
- Bump ossf/scorecard-action from 2.4.2 to 2.4.3 by @dependabot[bot] in https://github.com/LMCache/LMCache/pull/1753
- Bump step-security/harden-runner from 2.13.0 to 2.13.1 by @dependabot[bot] in https://github.com/LMCache/LMCache/pull/1752
- [CI/Build] Add P2P full test by @Shaoting-Feng in https://github.com/LMCache/LMCache/pull/1747
- [Model] Add Qwen3 model support for CacheBlend by @junl666 in https://github.com/LMCache/LMCache/pull/1633
- docs: Update model reference from Llama-3.1-70B to Llama-3.1-8B by @jay-tau in https://github.com/LMCache/LMCache/pull/1632
- [Doc] Update example code by @JZhou3083 in https://github.com/LMCache/LMCache/pull/1760
- [Doc] fix cpu offloading example doc by @cr7258 in https://github.com/LMCache/LMCache/pull/1740
- [Docs] Add kv cache calculator by @kobe0938 in https://github.com/LMCache/LMCache/pull/1763
- fix error in local cpu backend's clear() by @ziruiliu in https://github.com/LMCache/LMCache/pull/1766
- [Docs] Update expired lmcache slack link by @kobe0938 in https://github.com/LMCache/LMCache/pull/1774
- [Docs] Add vllm production stack for Kubernetes Deployment by @kobe0938 in https://github.com/LMCache/LMCache/pull/1764
- Introduce a basic check tool for verify lmcache env and config work as expected by @maobaolong in https://github.com/LMCache/LMCache/pull/1676
- implement clear_lookup_status in hit_limit_lookup_client by @chunxiaozheng in https://github.com/LMCache/LMCache/pull/1761
- [FSConnector] support read ahead in FSConnector by @chunxiaozheng in https://github.com/LMCache/LMCache/pull/1771
- [Core] SGLang Kernel Update & TP Balance by @Oasis-Git in https://github.com/LMCache/LMCache/pull/1510
- [observability]: P2P Stats Monitoring by @sammshen in https://github.com/LMCache/LMCache/pull/1754
- [Docs] Add KV Cache Sizes for Popular Models in faq by @kobe0938 in https://github.com/LMCache/LMCache/pull/1769
- Support adjust the effective memory by system available memory and reserve size by @maobaolong in https://github.com/LMCache/LMCache/pull/1708
- [feature][controller] support query worker info by @chunxiaozheng in https://github.com/LMCache/LMCache/pull/1462
- support start lookup server on other rank by @chunxiaozheng in https://github.com/LMCache/LMCache/pull/1466
- [Bugfix] Add KV Cache format in gds backend by @muma378 in https://github.com/LMCache/LMCache/pull/1324
- Add VRAM Calculator link by @kobe0938 in https://github.com/LMCache/LMCache/pull/1808
- [metrics] add request_cache_hit_rate metric by @chunxiaozheng in https://github.com/LMCache/LMCache/pull/1800
- Fix duplicate cache_policy.update_on_hit() calls in LocalDiskBackend by @KevinCheung2259 in https://github.com/LMCache/LMCache/pull/1809
- [bugfix]fix insert_key error in LocalDiskBackend by @chunxiaozheng in https://github.com/LMCache/LMCache/pull/1811
- [Core] Support NIXL storage obj backend by @tshmilnvidia in https://github.com/LMCache/LMCache/pull/1557
- Guarded the async serializer usage so we only wrap the backend load c… by @DongDongJu in https://github.com/LMCache/LMCache/pull/1795
- Bump github/codeql-action from 3 to 4 by @dependabot[bot] in https://github.com/LMCache/LMCache/pull/1784
- Add batched_async_contains related method to fs connector by @maobaolong in https://github.com/LMCache/LMCache/pull/1776
- Update README with LMCache citation and features by @YaoJiayi in https://github.com/LMCache/LMCache/pull/1829
- [Core] NixlStorageBackend support eviction by @tshmilnvidia in https://github.com/LMCache/LMCache/pull/1775
- Bump actions/stale from 10.0.0 to 10.1.0 by @dependabot[bot] in https://github.com/LMCache/LMCache/pull/1751
- Bump actions/setup-python from 5.6.0 to 6.0.0 by @dependabot[bot] in https://github.com/LMCache/LMCache/pull/1750
- disable async_serializer in pd by @novahow in https://github.com/LMCache/LMCache/pull/1818
- [CI/Build] Add comprehensive test for layerwise KV transfer by @Shaoting-Feng in https://github.com/LMCache/LMCache/pull/1822
New Contributors
- @lindseywn made their first contribution in https://github.com/LMCache/LMCache/pull/1638
- @SuperGoodGame made their first contribution in https://github.com/LMCache/LMCache/pull/1737
- @jay-tau made their first contribution in https://github.com/LMCache/LMCache/pull/1632
- @JZhou3083 made their first contribution in https://github.com/LMCache/LMCache/pull/1760
- @cr7258 made their first contribution in https://github.com/LMCache/LMCache/pull/1740
- @muma378 made their first contribution in https://github.com/LMCache/LMCache/pull/1324
- @KevinCheung2259 made their first contribution in https://github.com/LMCache/LMCache/pull/1809
- @DongDongJu made their first contribution in https://github.com/LMCache/LMCache/pull/1795
Full Changelog: https://github.com/LMCache/LMCache/compare/v0.3.7...v0.3.8