Skip to content

@vllm-project vLLM

Change the repository type filter

All

    Repositories list

    18 repositories

    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      amdcudainferencepytorchtransformerllamagptrocmmodel-servingtpu
      Python
      •
      Apache License 2.0
      •8.7k•52k•1.8k•789•Updated Jul 11, 2025Jul 11, 2025

    • vllm-gaudi

      Public
      Python
      •1•4•0•1•Updated Jul 11, 2025Jul 11, 2025

    • llm-compressor

      Public
      Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
      sparsitycompressionquantization
      Python
      •
      Apache License 2.0
      •174•1.6k•28•31•Updated Jul 11, 2025Jul 11, 2025

    • vllm-spyre

      Public
      Community maintained hardware plugin for vLLM on Spyre
      Python
      •
      Apache License 2.0
      •18•30•11•17•Updated Jul 11, 2025Jul 11, 2025

    • vllm-ascend

      Public
      Community maintained hardware plugin for vLLM on Ascend
      inferencetransformermodel-servingmlopsascendllmllmopsllm-servingvllm
      Python
      •
      Apache License 2.0
      •249•865•231•118•Updated Jul 11, 2025Jul 11, 2025

    • ci-infra

      Public
      This repo hosts code for vLLM CI & Performance Benchmark infrastructure.
      HCL
      •29•14•0•8•Updated Jul 11, 2025Jul 11, 2025

    • guidellm

      Public
      Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs
      Python
      •
      Apache License 2.0
      •52•394•45•10•Updated Jul 10, 2025Jul 10, 2025

    • production-stack

      Public
      vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
      Python
      •
      Apache License 2.0
      •223•1.5k•54•41•Updated Jul 10, 2025Jul 10, 2025

    • aibrix

      Public
      Cost-efficient and pluggable Infrastructure components for GenAI inference
      Go
      •
      Apache License 2.0
      •392•3.9k•195•17•Updated Jul 10, 2025Jul 10, 2025

    • flash-attention

      Public
      Fast and memory-efficient exact attention
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •1.8k•80•0•12•Updated Jul 9, 2025Jul 9, 2025

    • vllm-project.github.io

      Public
      HTML
      •18•11•0•0•Updated Jul 1, 2025Jul 1, 2025

    • vllm-openvino

      Public
      Python
      •
      Apache License 2.0
      •7•20•2•0•Updated Jun 5, 2025Jun 5, 2025

    • rfcs

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

    • FlashMLA

      Public
      Cuda
      •
      MIT License
      •875•5•0•0•Updated Apr 23, 2025Apr 23, 2025

    • vllm-project.github.io-static

      Public archive
      HTML
      •
      MIT License
      •7•8•0•1•Updated Feb 7, 2025Feb 7, 2025

    • media-kit

      Public
      vLLM Logo Assets
      1•3•0•0•Updated Dec 12, 2024Dec 12, 2024

    • vllm-nccl

      Public archive
      Manages vllm-nccl dependency
      Python
      •
      Apache License 2.0
      •3•17•2•0•Updated Jun 3, 2024Jun 3, 2024

    • dashboard

      Public
      vLLM performance dashboard
      Python
      •
      Apache License 2.0
      •7•32•0•0•Updated Apr 26, 2024Apr 26, 2024