Skip to content

Pinned Loading

  1. vllm vllm Public

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

    Python 60.7k 10.7k

  2. llm-compressor llm-compressor Public

    Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

    Python 2.1k 264

  3. recipes recipes Public

    Common recipes to run vLLM

    Jupyter Notebook 169 61

Repositories

Showing 10 of 26 repositories
  • tpu-inference Public

    TPU inference for vLLM, with unified JAX and PyTorch support.

    vllm-project/tpu-inference’s past year of commit activity
    Python 118 Apache-2.0 16 6 (1 issue needs help) 36 Updated Oct 22, 2025
  • llm-compressor Public

    Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

    vllm-project/llm-compressor’s past year of commit activity
    Python 2,132 Apache-2.0 264 57 (12 issues need help) 46 Updated Oct 22, 2025
  • compressed-tensors Public

    A safetensors extension to efficiently store sparse quantized tensors on disk

    vllm-project/compressed-tensors’s past year of commit activity
    Python 180 Apache-2.0 33 5 (1 issue needs help) 16 Updated Oct 22, 2025
  • recipes Public

    Common recipes to run vLLM

    vllm-project/recipes’s past year of commit activity
    Jupyter Notebook 169 Apache-2.0 61 4 4 Updated Oct 23, 2025
  • vllm Public

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

    vllm-project/vllm’s past year of commit activity
    Python 60,744 Apache-2.0 10,718 1,851 (31 issues need help) 1,181 Updated Oct 22, 2025
  • vllm-gaudi Public

    Community maintained hardware plugin for vLLM on Intel Gaudi

    vllm-project/vllm-gaudi’s past year of commit activity
    Python 12 Apache-2.0 56 1 63 Updated Oct 22, 2025
  • FlashMLA Public Forked from deepseek-ai/FlashMLA
    vllm-project/FlashMLA’s past year of commit activity
    C++ 6 MIT 896 0 3 Updated Oct 22, 2025
  • speculators Public

    A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM

    vllm-project/speculators’s past year of commit activity
    Python 60 Apache-2.0 11 4 (2 issues need help) 15 Updated Oct 22, 2025
  • vllm-project/vllm-project.github.io’s past year of commit activity
    HTML 20 33 0 1 Updated Oct 22, 2025
  • vllm-ascend Public

    Community maintained hardware plugin for vLLM on Ascend

    vllm-project/vllm-ascend’s past year of commit activity
    Python 1,240 Apache-2.0 507 596 (9 issues need help) 196 Updated Oct 22, 2025