CANN: Support MUL_MAT_ID for q8_0 and q4_0 (#13705)
* [CANN]Support MUL_MAT_ID Q8 && Q4 Signed-off-by: noemotiovon <757486878@qq.com> * codestyle adjustment Signed-off-by: noemotiovon <757486878@qq.com> --------- Signed-off-by: noemotiovon <757486878@qq.com>
This commit is contained in:
@@ -2035,6 +2035,15 @@ static bool ggml_backend_cann_supports_op(ggml_backend_dev_t dev,
|
||||
case GGML_TYPE_F16:
|
||||
case GGML_TYPE_F32:
|
||||
return true;
|
||||
case GGML_TYPE_Q8_0:
|
||||
case GGML_TYPE_Q4_0:
|
||||
#ifdef ASCEND_310P
|
||||
// Q4 && Q8 per group is not suppor on 310p device
|
||||
return false;
|
||||
#endif
|
||||
// only support contiguous for quantized types.
|
||||
return ggml_is_contiguous(op->src[0]) &&
|
||||
ggml_is_contiguous(op->src[1]);
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user