GitHub repo leaderboard by stars, growth rate and activity.

• vllm-project

  #1vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Python91,383 starslast pushed 24 hours ago
• jamiepine

  #2jamiepine/voicebox

  The open-source AI voice studio. Clone, dictate, create.

  TypeScript52,834 starslast pushed 5 weeks ago
• sgl-project

  #3sgl-project/sglang

  SGLang is a high-performance serving framework for large language models and multimodal models.

  Python35,728 starslast pushed Yesterday
• tracel-ai

  #4tracel-ai/burn

  Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

  Rust15,889 starslast pushed Yesterday
• kaldi-asr

  #5kaldi-asr/kaldi

  kaldi-asr/kaldi is the official location of the Kaldi project.

  Shell15,476 starslast pushed 12 months ago
• vosen

  #6vosen/ZLUDA

  CUDA on non-NVIDIA GPUs

  Rust14,818 starslast pushed 1 week ago
• NVIDIA

  #7NVIDIA/TensorRT-LLM

  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.

  Python14,580 starslast pushed 24 hours ago
• LMCache

  #8LMCache/LMCache

  LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

  Python11,733 starslast pushed Yesterday
• NVIDIA

  #9NVIDIA/cudf

  cuDF - GPU DataFrame Library

  C++9,749 starslast pushed 24 hours ago
• flashinfer-ai

  #10flashinfer-ai/flashinfer

  FlashInfer: Kernel Library for LLM Serving

  Cuda6,363 starslast pushed Yesterday

#	Repo	Language	Stars	30-day trend	Last updated
1	vllm-project vllm-project/vllm A high-throughput and memory-efficient inference and serving engine for LLMs	Python	91,383		last pushed 24 hours ago
2	jamiepine jamiepine/voicebox The open-source AI voice studio. Clone, dictate, create.	TypeScript	52,834		last pushed 5 weeks ago
3	sgl-project sgl-project/sglang SGLang is a high-performance serving framework for large language models and multimodal models.	Python	35,728		last pushed Yesterday
4	tracel-ai tracel-ai/burn Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.	Rust	15,889		last pushed Yesterday
5	kaldi-asr kaldi-asr/kaldi kaldi-asr/kaldi is the official location of the Kaldi project.	Shell	15,476		last pushed 12 months ago
6	vosen vosen/ZLUDA CUDA on non-NVIDIA GPUs	Rust	14,818		last pushed 1 week ago
7	NVIDIA NVIDIA/TensorRT-LLM 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	14,580		last pushed 24 hours ago
8	LMCache LMCache/LMCache LMCache: Supercharge Your LLM with the Fastest KV Cache Layer	Python	11,733		last pushed Yesterday
9	NVIDIA NVIDIA/cudf cuDF - GPU DataFrame Library	C++	9,749		last pushed 24 hours ago
10	flashinfer-ai flashinfer-ai/flashinfer FlashInfer: Kernel Library for LLM Serving	Cuda	6,363		last pushed Yesterday

All · 11,474