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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Added latency and throughput benchmark for beam search
- [Hybrid] Enable spec decoding in mamba cache align mode
- [Hybrid] Fix and optimize block-aligned splitting in mamba cache align mode
- [Doc]: Update CPU image docs to use Docker Hub after 0.16.0 release
- [Core] SWA-specific KV cache optimizations for prefix caching
- [Frontend] Enable generic structured_outputs for responses API
- [Core] Improve KV cache block reuse for prefix caching
- [Bug]: FLash Attn MLA Backend can't support headdim!=576
- [Bug]: Model architectures ['CostWiseGemmaForCausalLM'] are not supported for now.
- [Roadmap]: PD Disaggregation with `NixlConnector` Roadmap
- Docs
- Python not yet supported