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
- stash
- [Bug]: DFLASH2 force reprocesses context every reply
- [Bug][XPU]: Silent persistent output corruption (endless "!" / token 0) under sustained concurrent decode on Arc Pro B70, W4A16 27B head_dim 256
- [RFC]: Generalize Connector Metrics
- [RFC]: Reconcile Backpressure Admission
- [RFC]: Secondary Tier Usage Metrics
- [Bugfix] Avoid cloning target logits when logprobs are disabled
- [Benchmark] Fix MoE tuner cache cleanup and OOM recovery
- [Bug]: ExampleConnector keys external KV on raw prompt tokens, so cache_salt, LoRA and prompt_embeds do not partition it
- [Bugfix] Scale block size before padding a unified KV page
- Docs
- Python not yet supported