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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: benchmark_serving_multi_turn.py produces 0 final-content tokens on reasoning models because thinking budget consumes max_tokens
- [Bugfix] Fix macOS CPU platform detection by moving darwin fallback outside try/except
- [Bug]: Runtime LoRA unload does not remove adapter from engine
- linear: add CDNA-tuned W4A16 linear kernel
- Qwen3.5 + --enable-lora + TP=4 fails at startup in custom_all_reduce.cuh
- [Bugfix] Clamp NVFP4 MoE activation scales to prevent NaN from dead experts
- [Misc] Upgrade typos from v1.43.5 to v1.46.1 and fix new findings
- [MoE] Unwrap fused_moe for non-shared & non-DBO case
- Fix: gemma4 audio batching crash
- [Perf] Skip blocking GPU->CPU sync of num_accepted_tokens in hybrid+a…
- Docs
- Python not yet supported