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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: LLM.embed regression for text inputs after 0.19
- [Bug]: GPT-OSS Harmony: vLLM silently returns `content: null` with `finish_reason="stop"` when its parser ends in a non-terminal state
- [BugFix] Add kimi_k2 to MLA allowlist for EAGLE3 draft model detection
- [Bug]: MiniMax-M3-MXFP8 hangs on FlashInfer MNNVL all-reduce (torch symmetric_memory rendezvous) during CUDA graph capture on 2-node TP=8 non-MNNVL setup; fuse_allreduce_rms=False does not help
- [Doc] Clarify fastokens availability
- [Metrics] Add Prometheus metrics for LoRA adapter cache observability
- [Bug][ROCm][P/D] MoRI/MoRIIO READ-mode hangs and partial completions on AMD GPU P/D runs
- [Bug][ROCm][P/D] AITER FP8 experts and MLA/MTP decode need MI300X P/D fixes
- [Feature][ROCm] Support WideTP and WideEP P/D topologies on AMD GPUs
- [Feature][ROCm] Add relaxed speculative-token acceptance checks for AMD GPU runs
- Docs
- Python not yet supported