LMCache Files

Supercharge Your LLM with the Fastest KV Cache Layer

This is an exact mirror of the LMCache project, hosted at https://github.com/LMCache/LMCache. SourceForge is not affiliated with LMCache. For more information, see the SourceForge Open Source Mirror Directory.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
lmcache-0.3.9.post2-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl	2025-11-11	3.9 MB	0
lmcache-0.3.9.post2-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl	2025-11-11	3.9 MB	0
lmcache-0.3.9.post2-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl	2025-11-11	3.9 MB	0
lmcache-0.3.9.post2-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl	2025-11-11	3.9 MB	0
lmcache-0.3.9.post2.tar.gz	2025-11-11	1.1 MB	0
README.md	2025-11-11	1.2 kB	0
v0.3.9post2 source code.tar.gz	2025-11-11	1.1 MB	0
v0.3.9post2 source code.zip	2025-11-11	1.4 MB	0
Totals: 8 Items		19.3 MB	0

What's Changed

[logging]: less verbose async logs by @sammshen in https://github.com/LMCache/LMCache/pull/1820
[refactor] unified reconstruct cache engine key by @chunxiaozheng in https://github.com/LMCache/LMCache/pull/1955
[feat] Support get the env of current process by @maobaolong in https://github.com/LMCache/LMCache/pull/1944
Adapt hash func to vllm recent changes by @maobaolong in https://github.com/LMCache/LMCache/pull/1952
[CI/Build] Move /opt/venv/bin to PATH to BASE image by @ningziwen in https://github.com/LMCache/LMCache/pull/1962
[bugfix]: only update skip_leading_tokens on last PP rank in wait_for… by @tianlang-wq in https://github.com/LMCache/LMCache/pull/1827
Mooncake prioritizes obtaining the master address from master_ server_address by @tianlang-wq in https://github.com/LMCache/LMCache/pull/1971
[controller][bugfix] do not start lmcache worker on scheduler by @chunxiaozheng in https://github.com/LMCache/LMCache/pull/1965

New Contributors

@tianlang-wq made their first contribution in https://github.com/LMCache/LMCache/pull/1827

Full Changelog: https://github.com/LMCache/LMCache/compare/v0.3.9post1...v0.3.9post2

Source: README.md, updated 2025-11-11

Other Useful Business Software

Gen AI apps are built with MongoDB Atlas Icon

Gen AI apps are built with MongoDB Atlas

The database for AI-powered applications.

MongoDB Atlas is the developer-friendly database used to build, scale, and run gen AI and LLM-powered apps—without needing a separate vector database. Atlas offers built-in vector search, global availability across 115+ regions, and flexible document modeling. Start building AI apps faster, all in one place.

Start Free

Our Free Plans just got better! | Auth0 Icon

Our Free Plans just got better! | Auth0

With up to 25k MAUs and unlimited Okta connections, our Free Plan lets you focus on what you do best—building great apps.

You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.

Try free now

Recommended Projects

Aviary
Aviary is an LLM serving solution that makes it easy to deploy and manage a variety of open source LLMs. Providing an extensive suite of pre-configured open source LLMs, with defaults that work out of the box. Supporting Transformer models hosted on Hugging Face Hub or present on local disk....
vLLM
vLLM is a fast and easy-to-use library for LLM inference and serving. High-throughput serving with various decoding algorithms, including parallel sampling, beam search, and more.
Handy STT
Handy is a free, open-source, offline speech-to-text application built for privacy, accessibility, and extensibility. Developed using Tauri (Rust + React/TypeScript), it runs natively across Windows, macOS, and Linux while performing local speech recognition without sending any audio to cloud...
OhmGraphite
The above dashboard captures: - Power consumption of the CPU and GPU - CPU voltages and frequencies - Load breakdown on individual GPU components - CPU, GPU, disk, and motherboard temperature readings - Disk activity, space remaining, and error monitoring - Fan speed - Network consumption
Lemonade
Lemonade is a local LLM runtime that aims to deliver the highest possible performance on your own hardware by auto-configuring state-of-the-art inference engines for both NPUs and GPUs. The project positions itself as a “local LLM server” you can run on laptops and workstations, abstracting away...