COMMITS
/ backends/cadence/aot/quantizer/quantizer.py April 15, 2025
M
Remove layer norm from the default quantizer, add one that has it
mcremon-meta committed
April 8, 2025
M
Fix naming convention in quantizer
mcremon-meta committed
February 28, 2025
M
Enable quantized cat
mcremon-meta committed
February 20, 2025
M
Enable quantized add
mcremon-meta committed
February 19, 2025
M
Make the quantizer type a config argument
mcremon-meta committed
February 12, 2025
M
Use symmetric weights for convs and int8 in the default quantizer
mcremon-meta committed
January 24, 2025
D
Move XNNPACKQuantizer from PyTorch to ExecuTorch
Digant Desai committed
M
Make the quantized path the main testing path, and introduce a nop quantizer for fp32 cases
mcremon-meta committed
January 9, 2025
M
Refactor CadenceQuantizer
mcremon-meta committed
October 14, 2024
M
Use int8 quantizer in the OSS flow (#6166)
Matthias Cremon committed
July 30, 2024
M
Add exportable baby llama example (#4345)
Matthias Cremon committed
July 23, 2024
M
Enable aten.relu_.default in the CadenceQuantizer (#4344)
Matthias Cremon committed
July 16, 2024
M
Migrate the quantizer to use aten ops directly (#4195)
Matthias Cremon committed
July 12, 2024
M
Add support for quantized bmm (#4047)
Matthias Cremon committed
May 13, 2024
M
Cadence - refactor quantizer and passes (#3539)
Matthias Cremon committed