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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Require mistral-common 1.13.1 for `developer` role support
- [Rust Frontend] Support beam search (use_beam_search, length_penalty)
- [Feature][Core] Reset prefix cache without preempting running requests
- [Feature]: Anthropic-defined tools (web_search, bash, text_editor, ...) in /v1/messages
- [Model] Add SenseNova Loop support
- [CI][XPU] Use supported block sizes in UCX backend tests
- [Spec Decode][MRV2] Speculative round contract for custom speculators
- [Feature]: Allow `reset_prefix_cache` to clear cached prefixes without preempting running requests
- [Frontend] Accept managed global DP ranks in request headers
- [Misc] Use the b12x package shipped with flashinfer-python
- Docs
- Python not yet supported