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
- [Feature] Support MP-backed elastic expert parallelism for single-node DP scaling
- [Bugfix][Mamba] Warm up the SSD kernels on a prefill-sized sequence
- [Bugfix] Keep LRU cache views live and read-only
- [Bugfix][Quantization] Use absolute maxima for vision FP8 scaling
- [Bugfix][Parser] Fix GLM-4.7 stray <tool_call> in prose
- [Core] Add gap-tolerant prefix cache reuse
- [Bugfix][Parser] Keep text after a quoted Qwen <tool_call> marker
- [Bugfix][ROCm][MLA] Normalize FlashAttention LSE layout in mixed decode/prefill scheduling
- Fix duplicated word in cohere_asr processor comment
- [CI] Use readable titles for nightly perf-eval builds
- Docs
- Python not yet supported