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 supported31 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- fix disable_sliding_window for strict hf gemma4 config
- fix: preserve exception chain in EngineDeadError with proper context suppression (closes #42363)
- [BugFix] Fix MXFP8 checkpoint loading when quant_method collides with online shorthand
- [Bugfix] EXAONE 4.5: trim trailing MTP entry from text_config.layer_types
- docs: explain CUDA graph memory tuning
- docs: clarify Gemma 4 MTP assistant quantization
- docs: add TurboQuant KV cache presets
- [Docs] Expand llm-d integration page
- vLLM plumbing for cuteDSL hd512 FP8 kv cache kernel integration.
- [Doc] Sync four function docstrings with their signatures
- Docs
- Python not yet supported