MCPcopy Index your code
hub / github.com/NVIDIA/TensorRT-LLM / _any

Method _any

tensorrt_llm/quantization/mode.py:118–119  ·  view source on GitHub ↗
(self, bits)

Source from the content-addressed store, hash-verified

116
117 # Is one of the bits of the mask set?
118 def _any(self, bits):
119 return (self & bits) != 0
120
121 def is_int8_weight_only(self):
122 return self._all(self.INT8_WEIGHTS, self.WEIGHTS_AND_ACTIVATIONS)

Callers 15

is_qserve_w4a8Method · 0.95
has_fp8_block_scalesMethod · 0.95
has_per_group_scalingMethod · 0.95
has_int8_kv_cacheMethod · 0.95
has_fp8_kv_cacheMethod · 0.95
has_fp4_kv_cacheMethod · 0.95
has_fp8_qdqMethod · 0.95

Calls

no outgoing calls

Tested by 1

test_anyMethod · 0.64