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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- feat: Add apply_router_weight_on_input support for CPU MoE expert classes
- [Rust Frontend] Join text parts in the renderer for DeepSeek V3.2 and /v1/responses
- [Rust Frontend] Export vllm:request_render_duration_seconds
- [Rust Frontend] Export SimpleCPUOffload KV connector metrics
- [Rust Frontend] Support tool_reference content parts
- [Rust Frontend] Accept `spaces_between_special_tokens` as a no-op
- [Core] Reject the guidance backend for unsupported tokenizers in EngineCore
- [Bug]: Marlin NVFP4 zeroes E4M3 subnormal block scales with float16 activations, although its float16 path decodes them
- [Bugfix] Keep small NVFP4 block scales in Marlin with float16 activations
- [Bugfix][Quantization] Avoid Humming's fused-E8M0 path for MXFP4 layers it would round
- Docs
- Python not yet supported