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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm] MonoKernel for GLM 5.2
- [Bugfix] Dequantize DeepSeek-V4 wo_a for non-DeepGEMM linear backends
- [Bugfix][Attention] Use a block size only when every backend prefers it
- [Bug]: token_indices_to_sample underflows past the request's query start with PP > 1 spec decode
- [Bugfix] Pin long-lived host buffers at their exact size
- [Refactor] Move model-specific env vars into vllm/models/<model>/envs.py
- Lightning perf pr
- [Bug]: compressed-tensors MXFP4 MoE (`CutlassExpertsMxfp4`) crashes with an illegal memory access on GB200 (SM100) on main
- [Rust Frontend] packed_top_k_logprobs on raw generate
- [Bugfix] Fix DeepSeek-V4 FP8 O-projection crash with a forced --linear-backend
- Docs
- Python not yet supported