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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Performance]: 【求助】8卡H200跑DeepSeek-V4.1-Flash,并发才8就慢成狗,首字等好几分钟,有没有大佬遇到过?
- [Bug/Perf]: the dense default chosen for Mamba + EAGLE reverts to 0% prefix reuse under interleaved long conversations
- [Bugfix][Reasoning] Handle multi-token streaming deltas in the Hunyuan A13B parser
- [UX] Memory Usage Debugging
- [Model] Add NemotronLabsDiffusion support with tri-mode inference
- [Bugfix][Multimodal] Bound pinned host memory used for multimodal H2D copies
- [ROCm][MoRIIO] Fix WRITE prefill-block release routing under Wide-EP
- [Feature/Design]: UVA weight offload on quantized MoE — pin_memory() power-of-two rounding wastes ~35% host RAM, and MXFP4 process_weights_after_loading silently un-offloads layers via replace_parameter
- Revert "[Perf] Add fused DFlash2 grouped convolution (#55960)"
- [CI] Raise fault-detection deadline 45s -> 75s in FT E2E test
- Docs
- Python not yet supported