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 supported50 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Core][DP] Result-metric penalties and superlinear in-flight in DP lo…
- [Bugfix][Tool Parser] phi4_mini_json: report no tool call for an empty payload
- [Bugfix] Pin num_splits for the FA4 hd256 kernel in sparse MLA
- [XPU][UT] Fix MoE router precision mismatch in openai/privacy-filter
- [Feature]: Per-priority observability for --scheduling-policy priority
- [Bugfix][Model][CPU] Fix Mamba2 quantized in_proj weight and scale loading for TP >1
- [Bug]: KVCR secondary-tier configuration fails to start after the backpressure factory change
- [Bugfix][KV Offload] Restore KVCR construction through the secondary-tier factory
- [Bugfix][Core] Preserve negative float CLI values
- Fix allowed_token_ids/bad_words validation to reject impossible const…
- Docs
- Python not yet supported