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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Distributed] Lazily initialize unused NCCL2 process groups
- [Perf][ROCm] FlyDSL indexer logits on gfx950
- [Bugfix] Drop stray messages on the DP startup handshake socket instead of failing startup
- [Bugfix][EC Connector] Fail Mooncake requests on abandoned pushes immediately
- [WIP][DSv4.1] Opt in to mHC coefficient overlap on SM90
- [Bugfix][Frontend] Accept newline-separated parallel Hermes tool calls under tool_choice="required"
- [Kernel] Use dedicated kernels for Marlin scale preparation
- [Bugfix] Reuse Whisper encoder outputs across beam requests
- [Bugfix] Fix invalid streaming JSON for duplicate argument keys in HYV4 tool parser
- [Bug]: Sweep result paths collide and silently reuse measurements from another experiment
- Docs
- Python not yet supported