Repositories list

• ci-infra

  Public

  vllm-project/ci-infra’s past year of commit activity
  This repo hosts code for vLLM CI & Performance Benchmark infrastructure.

  HCL

  •

  Apache License 2.0

  •53•27•0•26•Updated Dec 28, 2025Dec 28, 2025

• vllm

  Public

  vllm-project/vllm’s past year of commit activity
  A high-throughput and memory-efficient inference and serving engine for LLMs

  amdcudainference+ 17pytorchtransformeropenaimoellamagptmodel-serving+ 10

  Python

  •

  Apache License 2.0

  •12k•66k•1.8k•1.3k•Updated Dec 28, 2025Dec 28, 2025

• vllm-ascend

  Public

  vllm-project/vllm-ascend’s past year of commit activity
  Community maintained hardware plugin for vLLM on Ascend

  inferencetransformermodel-serving+ 6mlopsascendllmllmopsllm-servingvllm

  Python

  •

  Apache License 2.0

  •684•1.5k•817•295•Updated Dec 28, 2025Dec 28, 2025

• vllm-metal

  Public

  vllm-project/vllm-metal’s past year of commit activity
  Community maintained hardware plugin for vLLM on Apple Silicon

  Python

  •

  Apache License 2.0

  •12•128•4•3•Updated Dec 28, 2025Dec 28, 2025

• guidellm

  Public

  vllm-project/guidellm’s past year of commit activity
  Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

  Python

  •

  Apache License 2.0

  •108•769•46•19•Updated Dec 28, 2025Dec 28, 2025

• tpu-inference

  Public

  vllm-project/tpu-inference’s past year of commit activity
  TPU inference for vLLM, with unified JAX and PyTorch support.

  Python

  •

  Apache License 2.0

  •64•202•16•79•Updated Dec 27, 2025Dec 27, 2025

• vllm-omni

  Public

  vllm-project/vllm-omni’s past year of commit activity
  A framework for efficient model inference with omni-modality models

  inferencepytorchtransformer+ 6image-generationdiffusionmodel-servingmultimodalvideo-generationaudio-generation

  Python

  •

  Apache License 2.0

  •225•1.8k•104•41•Updated Dec 27, 2025Dec 27, 2025

• vllm-project.github.io

  Public

  vllm-project/vllm-project.github.io’s past year of commit activity
  JavaScript

  •57•27•1•0•Updated Dec 27, 2025Dec 27, 2025

• vllm-daily

  Public

  vllm-project/vllm-daily’s past year of commit activity
  vLLM Daily Summarization of Merged PRs

  1•22•0•0•Updated Dec 27, 2025Dec 27, 2025

• semantic-router

  Public

  vllm-project/semantic-router’s past year of commit activity
  System Level Intelligent Router for Mixture-of-Models

  pythonkubernetesrust+ 17golangmcpfine-tuningenvoyproxypii-detectionmixture-of-modelshuggingface-transformers+ 10

  Go

  •

  Apache License 2.0

  •368•2.6k•95•38•Updated Dec 27, 2025Dec 27, 2025

• vllm-xpu-kernels

  Public

  vllm-project/vllm-xpu-kernels’s past year of commit activity
  The vLLM XPU kernels for Intel GPU

  C++

  •

  Apache License 2.0

  •16•14•1•3•Updated Dec 26, 2025Dec 26, 2025

• vllm-spyre

  Public

  vllm-project/vllm-spyre’s past year of commit activity
  Community maintained hardware plugin for vLLM on Spyre

  Python

  •

  Apache License 2.0

  •31•38•4•13•Updated Dec 26, 2025Dec 26, 2025

• router

  Public

  vllm-project/router’s past year of commit activity
  A high-performance and light-weight router for vLLM large scale deployment

  Rust

  •

  Apache License 2.0

  •13•66•4•4•Updated Dec 26, 2025Dec 26, 2025

• vllm-gaudi

  Public

  vllm-project/vllm-gaudi’s past year of commit activity
  Community maintained hardware plugin for vLLM on Intel Gaudi

  Python

  •

  Apache License 2.0

  •87•21•1•68•Updated Dec 24, 2025Dec 24, 2025

• vllm-neuron

  Public

  vllm-project/vllm-neuron’s past year of commit activity
  Community maintained hardware plugin for vLLM on AWS Neuron

  Python

  •4•16•2•1•Updated Dec 23, 2025Dec 23, 2025

• recipes

  Public

  vllm-project/recipes’s past year of commit activity
  Common recipes to run vLLM

  Jupyter Notebook

  •

  Apache License 2.0

  •112•306•9•30•Updated Dec 23, 2025Dec 23, 2025

• compressed-tensors

  Public

  vllm-project/compressed-tensors’s past year of commit activity
  A safetensors extension to efficiently store sparse quantized tensors on disk

  Python

  •

  Apache License 2.0

  •48•225•3•17•Updated Dec 23, 2025Dec 23, 2025

• aibrix

  Public

  vllm-project/aibrix’s past year of commit activity
  Cost-efficient and pluggable Infrastructure components for GenAI inference

  Go

  •

  Apache License 2.0

  •503•4.5k•268•29•Updated Dec 23, 2025Dec 23, 2025

• llm-compressor

  Public

  vllm-project/llm-compressor’s past year of commit activity
  Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

  sparsitycompressionquantization

  Python

  •

  Apache License 2.0

  •340•2.5k•75•49•Updated Dec 22, 2025Dec 22, 2025

• production-stack

  Public

  vllm-project/production-stack’s past year of commit activity
  vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization

  Python

  •

  Apache License 2.0

  •344•2.1k•92•55•Updated Dec 20, 2025Dec 20, 2025

• speculators

  Public

  vllm-project/speculators’s past year of commit activity
  A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM

  Python

  •

  Apache License 2.0

  •22•176•7•11•Updated Dec 19, 2025Dec 19, 2025

• flash-attention

  Public

  vllm-project/flash-attention’s past year of commit activity
  Fast and memory-efficient exact attention

  Python

  •

  BSD 3-Clause "New" or "Revised" License

  •2.3k•105•0•16•Updated Dec 17, 2025Dec 17, 2025

• FlashMLA

  Public

  vllm-project/FlashMLA’s past year of commit activity
  C++

  •

  MIT License

  •923•9•0•3•Updated Dec 15, 2025Dec 15, 2025

• vLLM-in-PyTorch-Conference-2025

  Public
  1•11•0•0•Updated Dec 14, 2025Dec 14, 2025

• vllm-openvino

  Public
  Python

  •

  Apache License 2.0

  •11•29•2•0•Updated Dec 4, 2025Dec 4, 2025

• media-kit

  Public
  vLLM Logo Assets

  4•6•0•0•Updated Oct 22, 2025Oct 22, 2025

• DeepGEMM

  Public
  DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

  Cuda

  •

  MIT License

  •784•0•0•0•Updated Sep 29, 2025Sep 29, 2025

• rfcs

  Public
  0•1•0•0•Updated Jun 3, 2025Jun 3, 2025

• vllm-project.github.io-static

  Public archive

  vllm-project/vllm-project.github.io-static’s past year of commit activity
  HTML

  •

  MIT License

  •7•9•0•1•Updated Feb 7, 2025Feb 7, 2025

• vllm-nccl

  Public archive

  vllm-project/vllm-nccl’s past year of commit activity
  Manages vllm-nccl dependency

  Python

  •

  Apache License 2.0

  •3•17•2•0•Updated Jun 3, 2024Jun 3, 2024