MCPcopy Create free account
hub / github.com/NVIDIA/TensorRT-LLM / is_int4_weight_only

Method is_int4_weight_only

tensorrt_llm/quantization/mode.py:124–125  ·  view source on GitHub ↗
(self)

Source from the content-addressed store, hash-verified

122 return self._all(self.INT8_WEIGHTS, self.WEIGHTS_AND_ACTIVATIONS)
123
124 def is_int4_weight_only(self):
125 return self._all(self.INT4_WEIGHTS, self.WEIGHTS_AND_ACTIVATIONS)
126
127 def is_weight_only(self):
128 return self.is_int4_weight_only() or self.is_int8_weight_only()

Callers 15

is_weight_onlyMethod · 0.95
test_weights_onlyMethod · 0.80
quant_dequant_intFunction · 0.80
set_weight_layerMethod · 0.80
add_tllm_weightFunction · 0.80
buildFunction · 0.80
get_weight_dtype_and_idFunction · 0.80
__init__Method · 0.80
__init__Method · 0.80
__init__Method · 0.80

Calls 1

_allMethod · 0.95

Tested by 3

test_weights_onlyMethod · 0.64
quant_dequant_intFunction · 0.64
set_weight_layerMethod · 0.64