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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Core] AsyncLLM.truncate_session: per-session KV cache truncation API
- [Feature] Tolerate malformed Harmony streams.
- [Frontend] use BAD_REQUEST for VLLMValidationError
- [Perf][ROCm] MoE int4 weight repacking for GPTQ/AWQ Triton kernel
- [MM][CG] ViT CudaGraph Video inference fall back to eager when input T > frames_per_item
- [V1][Bugfix] structured_output × spec-decode: pre-commit grammar filter for boundary-step bonus tokens
- [CI][Bugfix] Use token-id prefix in batch-invariant decode/prefill consistency test
- [Bugfix][Frontend] Fix (inadverted) regression when text is emitted before a tool call severely hurting agentic behavior
- [Core] Experimental session KV eviction with attention sinks
- [Model] Add hotwords support for model Qwen3-ASR
- Docs
- Python not yet supported