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 supported21 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [cuda 13][aarch64][CI] Adding CI steps to build arm64 cuda13 nightly wheels and images
- [Feature]: Fused Kernel for GPT-OSS Router
- [Performance]: Reevaluate padding requirement for Sequence Parallelism
- [DRAFT] Add RoaringBitmap-based sparse attention mask implementation
- [Feature]: Lightweight memory planner API for estimating model requirements
- Update abort the waiting queue of requests
- [CI/Build] Only install DeepEP kernels on CUDA version 12.8+
- [Performance]: Should I expect linear scaling with pure DP?
- [RFC]: Elastic DP Rank Recovery: Graceful Handling of GPU Hardware Failures Without Full Cluster Restart
- [CI Failure]:
- Docs
- Python not yet supported