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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- feat(parser): parser cache and deterministic tool call IDs for streaming derender
- [Bugfix][Frontend] Preserve GLM-4.7 MoE's unclosed final tool argument
- [Bug]: Responses API `truncation: "auto"` truncates at the token level from the left, dropping `instructions` first and cutting mid-item
- [Feature][Core] Add native SynthID-Text watermarker
- [RFC / Prototype] KV-PP (LayerSplit) KV cache planning and placement decoupling (#58329)
- [Model] Add Laya typed-decision models (Jev /v1/systemone via structured_server)
- [UX] Make deepgemm logging k8s friendly
- [Bugfix][MRV2] Keep prefill batches off varlen FULL decode graphs
- [Qwen4Exp] Checkpoint-mapped PLE storage for unified-memory GPUs (DGX Spark)
- [Bugfix] DiffusionGemma: finite entropy when top_k/top_p mask logits
- Docs
- Python not yet supported