MCPcopy Create free account
hub / github.com/NVIDIA/TensorRT-LLM / has_act_or_weight_quant

Method has_act_or_weight_quant

tensorrt_llm/quantization/mode.py:144–146  ·  view source on GitHub ↗
(self)

Source from the content-addressed store, hash-verified

142 self.WEIGHTS_AND_ACTIVATIONS)
143
144 def has_act_or_weight_quant(self):
145 return self._any(self.INT4_WEIGHTS | self.INT8_WEIGHTS
146 | self.ACTIVATIONS)
147
148 def has_per_token_dynamic_scaling(self):
149 return self._any(self.PER_TOKEN)

Callers 1

buildFunction · 0.80

Calls 1

_anyMethod · 0.95

Tested by

no test coverage detected