lmdeploy

Repository facts

Stars

8,108

Forks

781

Open issues and pull requests

616

Primary language

Python

License

Apache License 2.0 (Apache-2.0)

Owner

InternLM · Organization

Created

Jun 15, 2023

Last push

Oct 16, 2026

Topics

• codellama
• cuda-kernels
• deepspeed
• fastertransformer
• internlm
• llama
• llama2
• llama3
• llm
• llm-inference
• turbomind

Rank #1,005 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Related projects

Projects that share this one’s GitHub topics.

• 1,214

  Rank 1,214: yangjianxin1/Firefly

  Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya…

  6,647 starsPythonNo license file detectedLast push Oct 24, 2024

• 8,853

  Rank 8,853: xNul/code-llama-for-vscode

  Use Code Llama with Visual Studio Code and the Continue extension. A local LLM alternative to GitHub Copilot.

  568 starsPythonMITLast push Jul 31, 2024

• 742

  Rank 742: getumbrel/llama-gpt

  A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!

  10,921 starsTypeScriptMITLast push Apr 23, 2024

• 3,090

  Rank 3,090: xusenlinzy/api-for-open-llm

  Openai style api for open large language models, using LLMs just as chatgpt! Support for LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, Xverse, SqlCoder, CodeLLaMA, ChatGLM, ChatG…

  2,460 starsPythonApache-2.0Last push Sep 26, 2024

• 645

  Rank 645: bentoml/OpenLLM

  Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

  12,559 starsPythonApache-2.0Last push Oct 12, 2026

• 2,528

  Rank 2,528: b4rtaz/distributed-llama

  Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

  3,112 starsC++MITLast push Oct 14, 2026