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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Kernel][FP8][Test] Add CUDA qkv_padded_fp8_quant for ViT FP8
- [Bugfix] Respect NCCL_P2P_DISABLE in custom allreduce
- [Bugfix] Guard spec decode slot mapping padding rows
- fix: fallback to native forward for non-CUDA devices in FatreluAndMul (closes #42322)
- Handle structured output grammar compilation failures
- Stop setting CUDA_VISIBLE_DEVICES internally in vLLM, add device_ids arg
- [Doc] Fix inconsistent hash notation in prefix caching Time 5 diagram
- [Bug]: `humming-kernels` leaks two unreaped `python3` subprocesses (zombies) at import time, for every quantized model
- [Doc] Fix broken string literal in pipeline parallelism code example
- [Bug]:mistralai/Devstral-Small-2-24B-Instruct-2512 no longer working in 0.22.1
- Docs
- Python not yet supported