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 supported46 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Core] Preempt requests with fewer num_computed_tokens to reduce wasted computation
- [compile] fuse rope and cache insertion for mla
- [ROCm] Enable dual-stream MoE shared experts, AITER sparse MLA workaround, and GLM-5-FP8 weight loading fix
- [ECConnector] LMCache EC connector entrypoint
- Fix Marlin repack PTX incompatibility on H100/H200 (CUDA 12.8)
- [ROCm][perf] Use workspace manager for sparse indexer allocations
- [Bugfix] Fix TypeError in response_input_to_harmony when assistant content is None
- [ZenCPU] Changes with respect to docker build and relevant cpu tests
- Add opt-in `--record-power` option to `vllm bench serve`
- [torch.compile] Add compile-only mode
- Docs
- Python not yet supported