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
- [Bugfix][PCP][Spec Decode] Fix MTP draft prefill CUDA graphs under PCP
- Question: long-context generation stops mid-sentence with finish_reason=stop (final token = <|im_end|>) on Qwen3.8-27B with fp8 KV cache
- [ROCm][UMBP] Support UMBP standalone mode for DeepSeek-V4-Pro
- [RFC]: add eage4 spec decode
- [Bug]: "Loading weights took" logs the raw clock (~host uptime) when load_weights() doesn't pull from the weights iterator
- [ROCm][DSv4.1] Dispatch pre-quantized MXFP4 through MoRI for the A4W4 MoE
- [Bugfix][Multimodal] Make PaliGemma's whole prompt one bidirectional block
- [Perf][DSA] Budget sparse-indexer prefill chunks by the compressed logits width
- [ROCm][MiMo] Add TP8 MegaMoE backend
- [ROCm][DeepSeek-V4] Add TP8 MegaMoE backend
- Docs
- Python not yet supported