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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm] test_rocm_mxfp4_moe_oracle is stale, and the fused-TRITON case fails accuracy on gfx950
- [Bugfix] Disable FlashInfer autotune for trtllm_bf16_moe on SM100 during warmup to prevent TMA crash
- Fix for issue #15697
- [Model][Kernel] Add RWKV7 Albatross support
- [Bug]: [Regression] Qwen3.6-27B tool calls fail on Responses API when MTP is enabled
- [ROCm] [Perf] Optimize rocm aiter sparse mla indexer
- [Bugfix] Accept logprobs=-1 in the Completion API
- RFC: State-Aware Monolingual Reasoning Constraints for DeepSeek-R1 Models (Opt-In)
- [Feature]: Faster hybrid-SSM decode via input "replay" ring buffer (ReplaySSM)
- [ROCm][gpt-oss] Remove vLLM-side MoE padding rounding (AITER handles internally)
- Docs
- Python not yet supported