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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: XQA decode under FULL cudagraph capture silently corrupts attention output (fp8 and nvfp4 KV)
- [Bugfix][Tool Parser] Implement streaming for phi4_mini_json parser
- [Bug]: FlashInfer B12x W4A16 runtime repacking retains original and packed MoE weights, causing startup OOM
- fix(spec_decode): bypass embedding dim check for MTP speculative decoding methods
- [Bugfix] Propagate VLLM_MARLIN_INPUT_DTYPE into INC/AutoRound quant path
- [Bug]: VLLM_MARLIN_INPUT_DTYPE=int8 silently ignored for auto-round (INC) checkpoints
- [Kernel][Helion] Add numerics checks to benchmark script
- Remove all boilerplate from per-model `load_weights` methods
- [Bugfix][Platform] sm12x: add FLASHMLA_SPARSE (Triton sparse-MLA) to the MLA-sparse backend candidate list — flashinfer sparse_mla_sm120 livelocks on GB10
- [Bugfix][Spec Decode] Reach TP consensus on the drafter-pass gate before launching drafter collectives (fixes rank-divergent wedge at max_model_len boundary)
- Docs
- Python not yet supported