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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Perf][DSv4.1] Reuse prefill main-KV gathers across decoder groups
- [Perf][DSv4.1] Keep FP8 Engram rows packed through TP exchange
- [ROCm][Bugfix][DCP] Validate the retention interval against the right block size
- [Bugfix][Spec Decode] Implement get_top_tokens() on the generic MTP drafter
- [Quantization] Prefer Humming before Marlin backends on SM90
- [Bugfix][Test] Synchronise ranks before the profiled call in profile_…
- Add Agnes 3.0 Flash model support
- [ROCm][Bugfix] Pack W4A16 benchmark zero-points the way the op expects
- [CI] Relax MTP sharded sampling cross-boot noise bound
- [Benchmark] Add all-reduce rank-skew calibration
- Docs
- Python not yet supported