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
- [XPU] Add Support for Kimi-K3 and Kimi-Linear Models
- [Bug]: VLLM_MARLIN_INPUT_DTYPE=fp8 (Marlin W4A8-FP8) silently corrupts output on GB10/sm_121a — WNA16 INT4 MoE emits repeated </think> loop at temp 0 (kernel runs ~2.5% faster)
- [Kernel][Core][PCP][KV Update] Replace PCP update collectives with direct peer stores
- [Bugfix][Quantization] Keep unquantized routed experts unquantized under AutoGPTQ
- [Bugfix][MM] Profile the multimodal embedding merge during memory profiling
- [Feature] implement return indexer topk of sparse attention
- [Bug]: FlashInfer b12x SM120 MoE workspace allocated inside `profile_run` → OOM on 16 GB Blackwell (NVFP4 Qwen3.6-35B-A3B); regressed between vLLM dev552/FlashInfer 0.6.12 and v0.25.1/FlashInfer 0.6.13
- [Bug]: vllm bench serve - huggingface datasets - "TypeError: string indices must be integers, not 'str'"
- [Feature]: Support for Responses API `/v1/responses/input_tokens`
- [Test] Cover detokenize=False in offline beam search
- Docs
- Python not yet supported