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 supported36 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: LoRA `lora_expand` Triton kernel outputs NaN on Hopper (sm_90) with `block_n=128`, producing garbled LoRA output
- [Platform] Move env check function to platform interface
- [Bugfix][Frontend] Accept `tools: null` on the Responses API
- [CI] Add ModelOpt NVFP4 EPLB accuracy test (Qwen3-30B-A3B, 2xB200)
- V1 EngineCore: SIGTERM teardown runs two full-heap gen-2 GC passes (~4-7 s) to collect a few hundred objects
- [Bug]: Ministral3 RoPE scaling ignores YaRN mscale and nested Llama 4 fields
- [XPU] Dockerfile.xpu: LD_LIBRARY_PATH misses /opt/venv/lib -> torch sees 0 XPU devices in the built image
- [Bugfix] Initialize tracing in API server worker processes
- fix(models): pass quant_config to eh_proj in MTP layers to prevent silent precision loss
- [CI Failure]: `AMD: Language Models Test (Extended Pooling)` Workspace growth allocation after lock
- Docs
- Python not yet supported