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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Spec Decode] Synchronize adaptive DSpark decisions across TP ranks
- [Perf][Step5] Overlap the shared expert with routing at small batch
- [CI][XPU] Run Intel CI test steps on Kubernetes
- fix(xpu): Add opt-in W8A16 path for XPU block FP8 to improve performance
- [Bugfix] Fix out-of-bounds write of non-inplace final_state in fused recurrent delta-rule kernels
- [Bugfix] Fix out-of-bounds block-table read in Triton unified attention
- [Bugfix][Scheduler] Drop the drafter shift from the unchunked mm rollback
- [Bugfix][Pooling] Honor the CrossEncoder activation saved by Sentence Transformers v6
- [Bugfix][Frontend] Ignore Anthropic thinking budgets the server cannot enforce
- [Bugfix][Frontend] Only stream echoed prompt_token_ids when return_token_ids is set
- Docs
- Python not yet supported