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][Tool Parser] Keep granite4 streamed text between tool calls
- [Model] Support Nemotron Lightning structured decisions
- [Bugfix][Frontend] Report the line of a run-batch request rejected by request validators
- feat(metrics): add per-step copy-on-write KV block counter
- [RFC]: Selected input-row hidden-state export for full-vocabulary OPD teachers
- [BI][DSv4.1] Support DSpark speculative decoding under batch invariance
- [BI][DSv4.1] Add opt-in tensor-core GEMM tiers under batch invariance
- [BI][DSv4.1] Add opt-in Mega kernels under batch invariance
- [Bug]: ASRDataset uses channel count as duration when filtering stereo audio bytes
- [Bug]: Duplicate MCP server names advertise tools from a different execution server
- Docs
- Python not yet supported