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) #124
Annotations
1 error
pre-commit
Process completed with exit code 1.
|