MCPcopy
hub / github.com/NVIDIA/TensorRT-LLM / forward

Method forward

tensorrt_llm/quantization/layers.py:96–97  ·  view source on GitHub ↗
(self, input)

Source from the content-addressed store, hash-verified

94 self.axis = axis
95
96 def forward(self, input):
97 return dequantize(input, self.scaling_factor.value, self.axis)
98
99
100class SmoothQuantLinear(Linear):

Callers 1

test_dequantizeMethod · 0.95

Calls 1

dequantizeFunction · 0.85

Tested by 1

test_dequantizeMethod · 0.76