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
- [ROCm] Release physical VRAM on sleep, scoped to the Python unmap path
- [Bug]: GptOssForCausalLM fails to load BF16 (dequantized) checkpoint — KeyError: 'layers.0.mlp.experts.w2_weight'
- [RFC][Core][Model] Voxtral realtime: unbounded-duration streaming via RoPE re-anchoring (experimental, default-off)
- docs: multi-server vLLM deployment issues and solutions
- [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] Support MLA model identification for draft models Kimi(deeps…
- [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
- Docs
- Python not yet supported