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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Model Runner V2] support cudagraph check based on attn backend
- [Bugfix] Fix weights offloading for sleep mode
- [Docs] Sync quantization list between README files
- [CI] Add pip caching to cleanup_pr_body workflow
- [Core]Consolidate RoPE-related parsing into ModelArchitectureConfig
- [CI Failure]: Kernels Attention
- [Feature]: Will it support Qwen3 TTS
- [Bug]: PD report DeepseekV32 AssertionError: num_kv_heads == 1
- [Bugfix] Fix remove_instance logic error in disagg_proxy_demo.py
- [Feature]: Support multi-turn conversation for OpenAI Response API
- Docs
- Python not yet supported