Home
last modified time | relevance | path

Searched refs:VkInt4WeightOnlyQuantizer (Results 1 – 3 of 3) sorted by relevance

/aosp_15_r20/external/executorch/backends/vulkan/_passes/
H A D__init__.py3 VkInt4WeightOnlyQuantizer,
H A Dint4_weight_only_quantizer.py158 class VkInt4WeightOnlyQuantizer(Quantizer): class
/aosp_15_r20/external/executorch/examples/models/llama/source_transformation/
H A Dquantize.py17 from executorch.backends.vulkan._passes import VkInt4WeightOnlyQuantizer
161 model = VkInt4WeightOnlyQuantizer(groupsize=q_group_size).quantize(model)