RetroFed Forum
Your home away from modern life.
A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers
Post Reply
AuthorMessage
cm0002 literature.cafe cm0002@literature.cafe
Joined: 2025-11-08
Quote

1   Original
Post Reply
Back to top