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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Model] Fix DualChunkRotaryEmbedding hard-coded cuda device crash
- [Bugfix] Fall back to native rotary when flash-attn is installed but fails to load
- [Rust Frontend] Add Hunyuan A13B tool parser
- [Bug] xgrammar backend ignores the model's other EOS ids, so guided decoding can stop mid-string
- [Bug][ROCm/gfx942]: GLM-5.2-FP8 — first request after GPU idle emits garbage; piecewise CUDA graph cold replay corrupts the request's own prefill (workaround: cudagraph_mode=FULL_DECODE_ONLY)
- [Structured Output] Pass model EOS ids to xgrammar tokenizer info
- [Docs] Note pooled aggregation semantics for mean_acceptance_length
- [Bugfix] Fix PP speculative decode cadence with sync scheduling
- [Bugfix][Structured Outputs] Reject empty JSON schemas
- [Feature] Add native forward-pass metrics emission
- Docs
- Python not yet supported