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
- [Perf] [Sampling] - fix fallback and optimise fallback gather path for top-k in _topk_topp_kernel
- [Performance]: XPU block FP8: W8A16 instead of W8A8 took B70 TP4 single-stream decode from 35.27 to 57.87 tok/s
- [Rust Frontend] Fix /detokenize returning 500 for out-of-range token IDs
- Inference support for H-Spec draft model (speculative decoding)
- [Bug]: Investigate uniform decision scores for a D3 checkpoint loaded as Qwen3.5
- [Bug]: FlashInfer fp4_gemm autotune changes temperature-0 tokens on Qwen3.8-27B NVFP4 (SM120)
- [Bug][Anthropic API] /v1/messages ignores assistant prefill: final assistant turn is closed and a new assistant turn is opened
- [ROCm][KV Connector] Support sleep mode with MoRIIOConnector in WRITE mode over RDMA
- [Bugfix][Mooncake] Forward decode errors through proxy
- [RFC]: Fuse DSpark confidence-head GEMV into a single TileLang kernel
- Docs
- Python not yet supported