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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Include generation config stop token IDs in sampling defaults
- [Bugfix] Pass quant_config to DiffusionGemma's ParallelLMHead
- [Bugfix] Stop baking NVFP4 weight_scale_2 into b12x MoE block scales
- [Bugfix] Preserve Machete act-order permutation storage across weight reload
- [Frontend] Speed up offline prompt tokenization by 2.4x
- feat: integrate ScaleSweep NVFP4 quantization kernel
- [Bugfix] Initialize MiniMax M3 reasoning from prompt mode
- [Kernel][Test] Avoid NULL_BLOCK_ID in GDN sigmoid-gating test state indices
- [Bugfix] Match WeightsMapper stacked remaps on path components
- [Kernel] Extend Marlin atomic-add reduction to fused MoE
- Docs
- Python not yet supported