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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Handle optional bool-or-string CLI args in get_kwargs
- [Bug]: DeepSeek-V4-Flash hangs after ~6 requests with cudagraph_mode=FULL_AND_PIECEWISE + chunked prefill on SM 12.x (GB10)
- [Bugfix] Ensure DeepGEMM metadata gets contiguous context_lens
- [Bug]: can't run deepseek v4 flash
- [Do Not Merge][Attention] Sync FA with upstream
- [Misc] Allow install empty package from pip
- [Examples][last/6] Resettle examples.
- Enable native FlashInfer full CUDA graph support for SpecDec w/out TRT-LLM
- [ROCm][CI] Upgrade quantized FP4 kernels coverage
- [MoE] Add FlashInfer CUTLASS FP8 ptpc MoE wiring
- Docs
- Python not yet supported