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
- [Build] Downgrade to CUDA 12.8 but use nvcc 12.9 to build by overriding in setup.py
- [Bugfix] Fix compressed-tensors fp8 block assert and FlashInfer scale propagation
- [Build] Add cuda 12.8 release wheel
- [Bug]: #32618 performance issue
- [WIP][Feature] Support GGUF models with qwen3vl architecture
- [Feature] Add KV cache usage metrics to iteration logging
- [DOC] Add INT8 W4A8 docs and Arm's supported quantization schemes
- [Bugfix] Add is_blackwell_class() for SM121/GB10 DGX Spark support
- [Spec Decode][CUDA Graphs] Enables Eagle drafter support for FULL CUDA Graph mode
- [Bug]: Spec Decode Stats still report drafted tokens if drafting is skipped
- Docs
- Python not yet supported