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
- [Feature]: Unwrap FusedMoE custom op
- [P/D] Prefill compute optimizations with bi-directional KV cache transfers between P and D nodes
- [Model] Add TranslateGemma support
- [Core] Add determinism warmup automation for batch invariant mode
- Fix #26037: Skip CUDA platform detection when displaying help
- [Performance]: Fuse padding onto GEMM by making the GEMM out-of-place
- [Feature]: Lightweight memory planner API for estimating model requirements
- Update abort the waiting queue of requests
- [RFC]: Elastic DP Rank Recovery: Graceful Handling of GPU Hardware Failures Without Full Cluster Restart
- [RFC]: online quantization user facing API
- Docs
- Python not yet supported