GitHub Open Source Insight
Computed at Sep 11, 2026GitHub repo leaderboard by stars, growth rate and activity.
vllm-project
A high-throughput and memory-efficient inference and serving engine for LLMs
Python91,451 starslast pushed 2 hours agoray-project
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Python43,770 starslast pushed 4 hours agoliguodongiot
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
HTML25,031 starslast pushed 2 months agoNVIDIA
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
Python14,592 starslast pushed 2 hours agobentoml
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
Python12,528 starslast pushed 4 days agoskypilot-org
The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
Python10,585 starslast pushed 2 hours agoThe easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
Python8,834 starslast pushed 3 days agogpustack
A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.
Python5,664 starslast pushed 20 hours agosuperduper-io
Superduper: End-to-end framework for building custom AI applications and agents.
Python5,320 starslast pushed 1 year agoPaddlePaddle
High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle
Python3,714 starslast pushed 2 weeks ago
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | vllm-project A high-throughput and memory-efficient inference and serving engine for LLMs | Python | 91,451 | last pushed 2 hours ago | |
| 2 | ray-project Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads. | Python | 43,770 | last pushed 4 hours ago | |
| 3 | liguodongiot 本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地） | HTML | 25,031 | last pushed 2 months ago | |
| 4 | NVIDIA TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way. | Python | 14,592 | last pushed 2 hours ago | |
| 5 | bentoml Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud. | Python | 12,528 | last pushed 4 days ago | |
| 6 | skypilot-org The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster. | Python | 10,585 | last pushed 2 hours ago | |
| 7 | bentoml The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more! | Python | 8,834 | last pushed 3 days ago | |
| 8 | gpustack A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances. | Python | 5,664 | last pushed 20 hours ago | |
| 9 | superduper-io Superduper: End-to-end framework for building custom AI applications and agents. | Python | 5,320 | last pushed 1 year ago | |
| 10 | PaddlePaddle High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle | Python | 3,714 | last pushed 2 weeks ago |
All · 11,658