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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Frontend] Serve Qwen3-VL on /v1/systemone
- [Bugfix][Metrics] Preserve FFN layer contributions under pipeline parallelism
- [Bugfix] Accept 16-byte cache strides in DeepSeek CuTeDSL gather
- [Bugfix][KV Connector] Fence block reuse for producer-role loads
- [Bugfix] Preserve shape tuples when decomposing size nodes
- [Bugfix][Model Loader] Reject colliding sharded checkpoint part filenames
- [Bugfix][Rust Frontend] Count tokens, not chunks, in vllm-bench output throughput
- [Bugfix][KV Cache] Preserve Mamba prefill offload handoffs
- [ROCm][Kernel] Add W4A8 MoE decode kernel for RDNA3/RDNA3.5 (gfx11)
- [Perf][Structured Output] Reuse grammar bitmask staging
- Docs
- Python not yet supported