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
- [Bugfix] Use is_integrated to detect UMA GPUs for memory reporting
- [Bug]: Not able to run Qwen3-8B-NVFP4 on B200
- [Performance]: MTP causes 76% latency regression on Qwen3-Next-80B-A3B-Instruct-FP8
- [Bug]: vllm 0.16.0 GLM-OCR model fails to load - glm_ocr not in _CONFIG_REGISTRY, requires transformers >= 5.1
- [Feature]: Support for transformers 5.2.0
- [CI] DBO with DP+EP accuracy regression on GSM8K evaluation
- [RFC]: Worker Controller for warm GPU worker pooling to reduce cold-start latency
- [speculative decoding] Add dynamic speculation length with confidence-threshold early exit
- [BugFix] Fix MoE g_idx params causing ValueError with actorder=null AWQ models
- [Bug]: vLLM startup memory check mis-detects available VRAM (reclaimable OS memory) on UMA Systems
- Docs
- Python not yet supported