* use quantize_f instead of hardcoded quantize_q8_1 in mul_mat * restore Q8_0 in the reorder support lists * fallback mul_mat_q to dequantize when weight is reordered * add debug prints to isolate the reorder issue |
||
|---|---|---|
| .. | ||
| cmake | ||
| include | ||
| src | ||
| .gitignore | ||
| CMakeLists.txt | ||