MCPcopy Create free account
hub / github.com/pytorch/executorch / VgfQuantizer

Class VgfQuantizer

backends/arm/quantizer/arm_quantizer.py:1260–1279  ·  view source on GitHub ↗

Quantizer supported by the Arm Vgf backend. .. warning:: Setting ``use_composable_quantizer=True`` enables an experimental API surface that may change without notice. Args: compile_spec (VgfCompileSpec): Backend compile specification for Vgf targets.

Source from the content-addressed store, hash-verified

1258
1259
1260class VgfQuantizer(TOSAQuantizer):
1261 """Quantizer supported by the Arm Vgf backend.
1262
1263 .. warning::
1264 Setting ``use_composable_quantizer=True`` enables an experimental API
1265 surface that may change without notice.
1266
1267 Args:
1268 compile_spec (VgfCompileSpec): Backend compile specification for Vgf
1269 targets.
1270 use_composable_quantizer (bool): Whether to use the composable quantizer implementation. See https://github.com/pytorch/executorch/issues/17701" for details.
1271
1272 """
1273
1274 def __init__(
1275 self,
1276 compile_spec: VgfCompileSpec,
1277 use_composable_quantizer: bool = False,
1278 ) -> None:
1279 super().__init__(compile_spec, use_composable_quantizer)

Callers 7

_quantizerFunction · 0.90
_export_quantized_a16w8Function · 0.90
__init__Method · 0.90
create_quantizerFunction · 0.90
mainFunction · 0.90
export_deit.pyFile · 0.90
get_vgf_quantizerFunction · 0.90

Calls

no outgoing calls

Tested by 3

_quantizerFunction · 0.72
_export_quantized_a16w8Function · 0.72
__init__Method · 0.72