Skip to content

@vllm-project vLLM

Change the repository type filter

All

    Repositories list

    47 repositories

    • afd-plugin

      Public
      vLLM plugin for attention-ffn disaggregation support
      Python
      •
      Apache License 2.0
      •17•65•17•6•Updated Aug 3, 2026Aug 3, 2026

    • recipes

      Public
      Common recipes to run vLLM
      JavaScript
      •
      Apache License 2.0
      •353•947•35•105•Updated Aug 3, 2026Aug 3, 2026

    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      amdcudainference
      amdcudainferencepytorchtransformeropenaimoellamagptmodel-serving
      Python
      •
      Apache License 2.0
      •20k•88k•2k•4.2k•Updated Aug 3, 2026Aug 3, 2026

    • guidellm

      Public
      Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs
      Python
      •
      Apache License 2.0
      •202•1.5k•50•19•Updated Aug 3, 2026Aug 3, 2026

    • tpu-inference

      Public
      TPU inference for vLLM, with unified JAX and PyTorch support.
      Python
      •
      Apache License 2.0
      •274•397•72•327•Updated Aug 3, 2026Aug 3, 2026

    • vllm-ascend

      Public
      Community maintained hardware plugin for vLLM on Ascend
      inferencetransformermodel-serving
      inferencetransformermodel-servingmlopsascendllmllmopsllm-servingvllm
      C++
      •
      Apache License 2.0
      •1.9k•2.5k•1.5k•1.1k•Updated Aug 3, 2026Aug 3, 2026

    • semantic-router

      Public
      Intelligent Mixture-of-Models Router for Efficient Heterogeneous LLMs Inference
      kubernetesrustgolang
      kubernetesrustgolangmcpfine-tuningpii-detectionmixture-of-modelshuggingface-transformersbert-classificationllm
      Go
      •
      Apache License 2.0
      •794•5.1k•197•89•Updated Aug 3, 2026Aug 3, 2026

    • FlashKDA

      Public
      Cuda
      •
      MIT License
      •0•10•0•0•Updated Aug 3, 2026Aug 3, 2026

    • aibrix

      Public
      Cost-efficient and pluggable Infrastructure components for GenAI inference
      Go
      •
      Apache License 2.0
      •639•5k•312•38•Updated Aug 2, 2026Aug 2, 2026

    • llm-compressor

      Public
      Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
      compressionquantization
      compressionquantization
      Python
      •
      Apache License 2.0
      •600•3.6k•46•86•Updated Aug 2, 2026Aug 2, 2026

    • compressed-tensors

      Public
      A safetensors extension to efficiently store sparse quantized tensors on disk
      Python
      •
      Apache License 2.0
      •108•308•7•44•Updated Aug 2, 2026Aug 2, 2026

    • agentic-api

      Public
      Stateful API logic for agentic applications using vLLM
      Rust
      •
      Apache License 2.0
      •23•60•31•11•Updated Aug 2, 2026Aug 2, 2026

    • vllm-omni

      Public
      A framework for efficient model inference with omni-modality models
      inferencepytorchtransformer
      inferencepytorchtransformerimage-generationdiffusionmodel-servingmultimodalvideo-generationaudio-generationworld-model
      Python
      •
      Apache License 2.0
      •1.4k•5.8k•609•715•Updated Aug 2, 2026Aug 2, 2026

    • vllm-metal

      Public
      Community maintained hardware plugin for vLLM on Apple Silicon
      Python
      •
      Apache License 2.0
      •201•1.5k•8•4•Updated Aug 2, 2026Aug 2, 2026

    • vvm

      Public
      Manage multiple vLLM installations with isolated Python virtual environments. Switch between releases, commits, branches, and PRs instantly.
      Rust
      •
      Apache License 2.0
      •0•9•0•0•Updated Aug 2, 2026Aug 2, 2026

    • vllm-project.github.io

      Public
      HTML
      •124•59•4•16•Updated Jul 31, 2026Jul 31, 2026

    • speculators

      Public
      A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
      Python
      •
      Apache License 2.0
      •176•684•37•59•Updated Jul 31, 2026Jul 31, 2026

    • vllm-bnb-plugin

      Public
      vLLM Quantization plugin for bitsandbytes
      Python
      •
      Apache License 2.0
      •1•2•0•1•Updated Jul 31, 2026Jul 31, 2026

    • vllm-gaudi

      Public
      Community maintained hardware plugin for vLLM on Intel Gaudi
      Python
      •
      Apache License 2.0
      •146•50•4•59•Updated Jul 31, 2026Jul 31, 2026

    • vllm-gguf-plugin

      Public
      vLLM Quantization plugin for GGUF
      Python
      •
      Apache License 2.0
      •29•29•4•9•Updated Jul 31, 2026Jul 31, 2026

    • perf-eval

      Public
      Performance benchmark & accuracy evaluation for vLLM
      Python
      •15•12•0•23•Updated Jul 31, 2026Jul 31, 2026

    • flash-attention

      Public
      Fast and memory-efficient exact attention
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •3k•133•0•41•Updated Jul 31, 2026Jul 31, 2026

    • ci-infra

      Public
      This repo hosts code for vLLM CI & Performance Benchmark infrastructure.
      Python
      •
      Apache License 2.0
      •75•45•0•58•Updated Jul 30, 2026Jul 30, 2026

    • MSA

      Public
      Python
      •
      MIT License
      •49•0•0•0•Updated Jul 30, 2026Jul 30, 2026

    • production-stack

      Public
      vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
      Python
      •
      Apache License 2.0
      •457•2.5k•99•83•Updated Jul 30, 2026Jul 30, 2026

    • vllm-dashboard

      Public
      TypeScript
      •9•10•1•2•Updated Jul 30, 2026Jul 30, 2026

    • vllm-daily

      Public
      vLLM Daily Summarization of Merged PRs
      5•52•0•0•Updated Jul 30, 2026Jul 30, 2026

    • vllm-xpu-kernels

      Public
      The vLLM XPU kernels for Intel GPU
      C++
      •
      Apache License 2.0
      •92•57•12•53•Updated Jul 30, 2026Jul 30, 2026

    • DeepGEMM

      Public
      DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
      Cuda
      •
      MIT License
      •1.1k•0•0•0•Updated Jul 30, 2026Jul 30, 2026

    • vllm-bench

      Public
      High-performance Rust benchmark client for vLLM serving endpoints.
      Rust
      •
      Apache License 2.0
      •11•51•1•3•Updated Jul 28, 2026Jul 28, 2026
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.