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

Method has_act_and_weight_quant

tensorrt_llm/quantization/mode.py:140–142  ·  view source on GitHub ↗
(self)

Source from the content-addressed store, hash-verified

138 return self.is_int4_weight_only() and self._any(self.PER_GROUP)
139
140 def has_act_and_weight_quant(self):
141 return self._all(self.INT8_WEIGHTS | self.ACTIVATIONS,
142 self.WEIGHTS_AND_ACTIVATIONS)
143
144 def has_act_or_weight_quant(self):
145 return self._any(self.INT4_WEIGHTS | self.INT8_WEIGHTS

Callers 15

to_dictMethod · 0.95
build_gptFunction · 0.80
forwardMethod · 0.80
buildFunction · 0.80
__init__Method · 0.80
__init__Method · 0.80
__init__Method · 0.80
__init__Method · 0.80
forwardMethod · 0.80
forwardMethod · 0.80
__init__Method · 0.80
forwardMethod · 0.80

Calls 1

_allMethod · 0.95

Tested by 1

forwardMethod · 0.64