COMMITS
/ backends/cadence/aot/functions.yaml April 1, 2025
M
Add im2row per tensor overload
mcremon-meta committed
March 11, 2025
J
[Cadence] add reference requantize out and tests
JP committed
March 7, 2025
J
March 6, 2025
J
[Cadence] add quant relu per tensor for cpu flow
JP committed
December 10, 2024
H
cadence quantized_linear_per_tensor_out cpu
Hansong committed
December 7, 2024
December 5, 2024
December 4, 2024
Z
add missing aten ops for x86 flow
Zonglin Peng committed
Z
Populate cadence cpu ops (#7165)
Zonglin Peng committed
November 21, 2024
M
Add mobilenet_v2 and resnet50 to the examples
mcremon-meta committed
November 2, 2024
M
Add per_tensor overload for quantized_layer_norm
mcremon-meta committed
August 19, 2024
Z
added empty out
zonglinpengmeta committed
August 15, 2024
Z
added expand and gelu ops
zonglinpengmeta committed
August 9, 2024
Z
fixed quantized_matmul_out
zonglinpengmeta committed
August 3, 2024
M
Make quantized relu more flexible with quant params and use nnlib kernel on HiFi (#4530)
Matthias Cremon committed
July 30, 2024
M
Add exportable baby llama example (#4345)
Matthias Cremon committed
July 16, 2024
M
Provide kernels with true reference implementations for quantized ops (#4108)
Matthias Cremon committed
June 5, 2024
M
Cadence examples -- Add RNNT encoder from torchaudio (#3691)
Matthias Cremon committed
May 7, 2024
M
Cadence - Move primary code to backends folder (#3353)
Matthias Cremon committed