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
- [Feature][Help Wanted]: Add tuning script and config files for Mamba selective_state_update kernel
- [Feature]: max-num-partial-prefills in V1
- [Bug]: MXFP4 models still fall back to the Marlin kernel for RTX PRO 6000 (Blackwell SM120)
- enable vllm ut for Intel GPU
- [Feature]: Integrate RMS+fp4 fused kernel from FlashInfer
- [Bugfix] Auto-configure TRITON_PTXAS_PATH for new GPU architectures
- Bugfix: zero-initialized metrics for failed/aborted/skipped requests throwing off histograms
- [Kernel] adding native nccl4py support
- Drafter Supports Multiple KVCache Groups
- [Bug]: default_weight_loader receives unexpected `weight_name` kwarg in GPT-OSS load_weights
- Docs
- Python not yet supported