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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [XPU][Spec Decode] RecoverSSM: route Qwen GDN through the Triton/FLA core on XPU
- [Spec Decode][Mamba] RecoverSSM: support pipeline parallelism (non-last ranks commit in the deferred PP postprocess)
- [Startup] Add an opt-in FlashInfer MoE search strategy
- [Build] Re-fetch DeepGEMM when the cached checkout is not the pinned commit
- [Bugfix] Free the pinned CPU weight backup on wake_up
- [Bug]: OffloadingConnector with LHBNC returns wrong output on CPU hits
- [Refactor] Consolidate environment variable declarations into single source of truth
- [XPU] add ucx ipc into dockerfile
- [Spec Decode][Test] Add regression test for draft slot_mapping block size on hybrid models
- [WIP][Model] Share recurrent arithmetic for Qwen GDN batch invariance
- Docs
- Python not yet supported