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
- [Do Not Merge][Attention] Enable masked MHA for topk sparse attention using FA4
- Handle setpgrp permission errors in forked test harness
- Fix vllm build for power
- [Core] Enable FP8 KV cache with Decode Context Parallel (DCP) for MLA
- [ROCm] Enable DBO (Dynamic Batch Optimization) on ROCm
- Fix memory leak in Responses API store
- refactor(attention): add default get_kv_cache_stride_order implementation
- [Bug]: AllReduceFusionPass(config) takes 1s+ to construct
- [Bug]: vLLM that leaves orphan processes running when the parent process dies due to OOM
- [Performance]: Significant performance drop in v0.15.1 with Qwen3-480B?
- Docs
- Python not yet supported