MCPcopy
hub / github.com/NVIDIA/TensorRT-LLM / has_fp8_rowwise

Method has_fp8_rowwise

tensorrt_llm/quantization/mode.py:180–181  ·  view source on GitHub ↗
(self)

Source from the content-addressed store, hash-verified

178 return self._any(self.FP8_QDQ)
179
180 def has_fp8_rowwise(self):
181 return self._any(self.FP8_ROWWISE)
182
183 def has_nvfp4(self):
184 return self._any(self.NVFP4)

Callers 15

has_act_static_scalingMethod · 0.95
to_dictMethod · 0.95
buildFunction · 0.45
__init__Method · 0.45
forwardMethod · 0.45
__init__Method · 0.45
__init__Method · 0.45
forwardMethod · 0.45
forwardMethod · 0.45
forwardMethod · 0.45
forwardMethod · 0.45
forwardMethod · 0.45

Calls 1

_anyMethod · 0.95

Tested by

no test coverage detected