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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] EPLB - Mistral
- fix: correct load_weights track logic and enable weight integrity for…
- [New Model][Nvidia] Add SM12x support for DeepSeek V4 Flash with essential fixes
- platforms: handle MIG device UUID in device_id_to_physical_device_id
- [Docs] Reorganize online serving docs.
- [MoE Refactor] Optional router_logits argument
- [Bug]: `runai_streamer` with `distributed=true` produces empty output for Nemotron-H (Nano-Omni-30B) model
- [ROCm] Fix allreduce + RMSNorm fusion pattern matchin
- [XPU] keep generator state of sycl kernel align with pytorch
- [Bugfix] Flush final KV block when SimpleCPUOffload request finishes in same step as its last full block
- Docs
- Python not yet supported