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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: MFU statistics on the Step-3.5-Flash model are inaccurate
- [Feature]: Universal Speculative Decoding for Heterogeneous Vocabularies (TLI / Token-Level Intersection)
- [RFC]: Support ViT Full CUDA Graph (Tracker)
- [Bug]: Based on Qwen3.5-35B-A3B, why does enabling MTP speculative decoding actually reduce the prefix cache hit rate?
- [code clean] remove useless contextlib.suppress(Exception)
- [Performance]: Prefix cache hit lower on vLLM than on other inference stacks
- [Bug]: Qwen3.5-dense wfp8afp8 w: per-tensor a: per-tensor Output garbled text, but in sglang is norm
- [Feature]: Add apply_with_spec_decode() method to LogitBiasLogitsProcessor for speculative decoding support
- [Bug]: M2.5 tool call result is badcase, deploy 1p1d with nixl connector, P and D use DP8-EP-TP1
- Enable multiple gpu test on xpu platform
- Docs
- Python not yet supported