[Perf][Kernel] Optimize FP4 quantization kernels (SM100F) (#32520)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
This commit is contained in:
@@ -1307,7 +1307,9 @@ class ModelOptNvFp4LinearMethod(LinearMethodBase):
|
||||
output_shape = [x.shape[0], layer.weight.shape[0]]
|
||||
|
||||
# quantize BF16 or FP16 to (FP4 and interleaved block scale)
|
||||
x_fp4, x_blockscale = scaled_fp4_quant(x, layer.input_scale_inv, self.backend)
|
||||
x_fp4, x_blockscale = scaled_fp4_quant(
|
||||
x, layer.input_scale_inv, is_sf_swizzled_layout=True, backend=self.backend
|
||||
)
|
||||
|
||||
# validate dtypes of quantized input, input block scale,
|
||||
# weight and weight_blockscale
|
||||
|
||||
Reference in New Issue
Block a user