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
- [Bugfix] Release ParentRequest state when an n>1 request is aborted
- [RFC]: Generic Control RPC for KV Connectors
- [Bug]: Massive output-token throughput regression since v0.24.0 with Qwen3.6-35B-A3B-FP8
- [Bugfix][Reasoning] Fix streaming reasoning content misrouted to content when stop parameter desyncs delta_text from delta_token_ids
- [Bugfix][Frontend] Accept Anthropic x-api-key auth header
- [Bug]: NVML UUID resolution fails for NVIDIA's documented short-form CUDA_VISIBLE_DEVICES UUIDs
- [Bugfix][Kernel] Take a native fp8 KV cache in TRITON_MLA, and fold the non-causal decode
- [Bugfix][KV Cache] Fix incremental multimodal block hashing
- [Bugfix][Tool Parser] Fix xLAM streaming: duplicated arguments on finalize, markers leaking into content
- [Core] Distinguish reused from newly cached blocks in BlockStored
- Docs
- Python not yet supported