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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: MTP speculative decoding produces corrupted output at concurrency >= 4 (V1 engine)
- [Perf] flashinfer gdn decode kernel intergration
- [Bugfix Proposal]: Support MIG UUIDs in CUDA_VISIBLE_DEVICES (int() conversion and NVML handle resolution)
- fixed mtp, multi rank, and test passed
- [Performance]: DeepSeek 3.2 Multi-stream indexer
- [Feature]: Make the Qwen3-ASR use `request_prompt` from user input
- [Bug]: OpenAI transcribe prompt parameter with whisper return hallucinated transcription
- [Bugfix] [DeepSeek-V3.2] fix sparse_attn_indexer weights padding
- [torch.compile]: Optimize collectives in TP MoE case using torch.compile pass
- TRTLLM gen-full attn spec decode & FP8 KV dequant tests
- Docs
- Python not yet supported