Skip to content
This repository was archived by the owner on Sep 20, 2025. It is now read-only.

Add deepseek-r1 1.58bit/2.51bit/4bit quantization model support with various gpu, including g5 (8x, 12x, 16x, 24x, 48x), g6 (8x, 12x, 16x, 24x, 24x), g6e (4x, 8x, 12x, 16x, 24x, 48x) #125

Add deepseek-r1 1.58bit/2.51bit/4bit quantization model support with various gpu, including g5 (8x, 12x, 16x, 24x, 48x), g6 (8x, 12x, 16x, 24x, 24x), g6e (4x, 8x, 12x, 16x, 24x, 48x)

Add deepseek-r1 1.58bit/2.51bit/4bit quantization model support with various gpu, including g5 (8x, 12x, 16x, 24x, 48x), g6 (8x, 12x, 16x, 24x, 24x), g6e (4x, 8x, 12x, 16x, 24x, 48x) #125