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
- [Perf] Add tuning configs for SM103 Kimi k3 nvfp4 DEP projection GEMM
- [Bugfix][Scheduler] Handle missing req_id in update_from_output gracefully
- [Bugfix][Tokenizer] Handle trailing system messages in DeepSeek V3.2 rendering
- [Core][Frontend] Add per-request prefix cache telemetry
- [MM] Add a Mooncake-store backend for the multi-modal processor cache
- [Multiproc] Fail fast on concurrent worker exceptions via background error pipe monitor
- fix(warmup): cover all C128A extra_topk widths in sparse-MLA autotune
- [Bug][Spec Decode] DFlash2: draft model unloadable — decoder_layer_cls ignored in DFlashQwen3Model.__init__ + full-vocab init transients OOM 24GB cards
- [Bug]: test_spec_decode_logprobs never runs on NVIDIA CI, and is ill-defined at top-k ties when it does
- [Core][Scheduler] Gracefully handle unexpected request status on KV transfer finish
- Docs
- Python not yet supported