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
- [Bugfix][Hardware][AMD] Support all MoE activations in WNA16 quantization on ROCm
- add acceptance_threshold argument
- Add encoder cache computation time tracking for replacement algorithm design
- [Feature] Add num_steps and delay_steps parameters to /start_profile endpoint
- [Spec Decode] Finite state machine speculative decoding
- [MIX] More accurate processing of quantization of `mlp.gate`
- [Bug]: MTP speculative decoding produces corrupted output at concurrency >= 4 (V1 engine)
- [Perf] flashinfer gdn decode kernel intergration
- [torch.compile]: Optimize collectives in TP MoE case using torch.compile pass
- TRTLLM gen-full attn spec decode & FP8 KV dequant tests
- Docs
- Python not yet supported