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 supported25 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Core] Add --deterministic-prefix-caching for reproducible prefill on ROCm
- [Kernel] Support fused_moe tuning with gemma-4-26B-A4B-it
- [Distributed] Add MSCCL++ allreduce support for multi-node communication
- [Perf] Add fast all2all kernel, tested for DCP, 1.1% Throughput improvement
- [entrypoints/openai] add kv params to streaming api response
- [Perf] Cache get_sm_version_num() in cutlass dispatch
- [Core] Use fastsafetensors ParallelLoader for weight loading
- [Bug]: DeepSeek OCR doesn't work on vllm 0.19
- [Bug]: `response_format` suppresses tool calls when `tool_choice: "auto"` — constrained decoding prevents tool generation
- [Bug] Level-2 sleep/wake crashes with KeyError when enable_lora=True
- Docs
- Python not yet supported