vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [WIP][CI][build] Move torch deps into requirements/torch.txt and torchlib.txt
- [Core] [MLA] Optimize the copy for k_nope, k_pe and v
- [Installation]: Newly required -cc tag in 0.14.0 for Docker compose -- documentation
- Refactor save_path creation for benchmark results of benchmark/kernels/bench_fp8_gemm.py
- [Bug]: importing `bitsandbytes` causes pytest to fail
- [Bug]: GPT-OSS 0% prefix cache hits with hybrid attention + EAGLE
- [Performance]: H200 Kimi K2 TP8 Triton MoE min-latency
- [Bug] [ROCm]: Loading Qwen3-MoE-MXFP4 Weights in v0.14.
- [ROCm] MI355X CI parity is missing
- Sm120 130
- Docs
- Python not yet supported