vllm-project 是一个在 GitHub 上活跃的组织，专注于大规模语言模型的推理和服务。该组织的公共代码库涵盖多种编程语言，包括 Python、C++、Rust 和 Go，拥有一系列广泛使用的项目，如 vllm、vllm-omni 和 aibrix，展示了其在人工智能领域的贡献。
顶级语言
公共仓库
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
vllm-omni
A framework for efficient model inference with omni-modality models
aibrix
Cost-efficient and pluggable Infrastructure components for GenAI inference
semantic-router
System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge
llm-compressor
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
production-stack
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
vllm-ascend
Community maintained hardware plugin for vLLM on Ascend
vllm-metal
Community maintained hardware plugin for vLLM on Apple Silicon
guidellm
Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs
recipes
Common recipes to run vLLM
speculators
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
tpu-inference
TPU inference for vLLM, with unified JAX and PyTorch support.
compressed-tensors
A safetensors extension to efficiently store sparse quantized tensors on disk
router
A high-performance and light-weight router for vLLM large scale deployment
vime
An LLM post-training framework with vLLM for RL Scaling
flash-attention
Fast and memory-efficient exact attention
vllm-skills
Agent skills for vLLM
vllm-openvino
此仓库未提供描述。
vllm-daily
vLLM Daily Summarization of Merged PRs
vllm-xpu-kernels
The vLLM XPU kernels for Intel GPU
vllm-project.github.io
此仓库未提供描述。
ci-infra
This repo hosts code for vLLM CI & Performance Benchmark infrastructure.
vllm-gaudi
Community maintained hardware plugin for vLLM on Intel Gaudi
agentic-api
Stateful API logic for agentic applications using vLLM
vllm-neuron
Community maintained hardware plugin for vLLM on AWS Neuron
dllm-plugin
vLLM plugin for block-based diffusion language model (dLLM) support
vllm-nccl
Manages vllm-nccl dependency
FlashMLA
此仓库未提供描述。
bart-plugin
vLLM Model plugin for the encoder-decoder BART model
vLLM-in-PyTorch-Conference-2025
此仓库未提供描述。
media-kit
vLLM Logo Assets
vllm-project.github.io-static
此仓库未提供描述。
vllm-gguf-plugin
vLLM Quantization plugin for GGUF
perf-eval
Performance benchmark & accuracy evaluation for vLLM
vllm-dashboard
此仓库未提供描述。
perf-dashboard
Performance dashboard for vLLM
vllm-bnb-plugin
vLLM Quantization plugin for bitsandbytes
rfcs
此仓库未提供描述。
MSA
此仓库未提供描述。
DeepGEMM
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
vllm-docs
此仓库未提供描述。
llm-multimodal
Standalone fork of llm-multimodal from SMG
常见问题
vllm-project 在 GitHub 上构建了什么？
vllm-project 在 GitHub 上构建了一系列与大规模语言模型相关的项目，主要包括推理和服务引擎，以及高效的模型推理框架。这些项目旨在为不同的应用场景提供解决方案。
vllm-project 使用哪些编程语言？
vllm-project 主要使用 Python、C++、Rust 和 Go 等编程语言。这些语言的多样性反映了该组织在构建高效和可扩展系统方面的能力。
vllm-project 的代码库是公开的吗？
是的，vllm-project 的所有代码库都是公开的。这意味着任何人都可以访问、审计和贡献这些项目，从而促进了开源社区的发展。