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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [DCP] Default query replication for GLM sparse attention
- [Bug]: Blocking issue of `MessageQueue.dequeue` in multi-threaded environments
- [Performance][MooncakeStoreConnector] Overlapping async cold-prefix loads cause duplicate Gets into distinct GPU blocks
- [Bugfix] Fix six quantization exception messages split across positional args
- [Bugfix] Reject KV caches FlexAttention cannot address in int32
- [Model] Apertus 1.5
- [Core][Distributed] Size custom all-reduce buffers at init so batch-invariant mode can use them
- [KV Offloading] Support partial-tail prefix reuse with fine-grained prefix matching
- [Bugfix][Core][Spec Decode] Exclude scheduler padding from draft metrics
- fix(config): guard LlamaBidirectionalConfig against missing hf_config.pooling
- Docs
- Python not yet supported