COMMITS
/ kernels/optimized/cpu/targets.bzl May 20, 2025
P
Dtype selective build for optimized ops (#10992)
pytorchbot committed
P
Move optimized target definitions to op_registration.bzl (#10986)
pytorchbot committed
April 23, 2025
S
BroadcastIndexesRange: leading 1s don't require true broadcasting (#9431)
Scott Wolchok committed
April 19, 2025
P
Implement _fft_c2r core ATen op
pssrawat committed
April 16, 2025
M
Complex Support: bmm
Manuel Candales committed
April 5, 2025
April 4, 2025
S
Add optimized ELU implementation (#9521)
Scott Wolchok committed
March 27, 2025
S
Revert "Depend on extension/threadpool, not thread_parallel_interface, in buck (#9511)" (#9727)
Scott Wolchok committed
March 26, 2025
S
Depend on extension/threadpool, not thread_parallel_interface, in buck (#9511)
Scott Wolchok committed
March 22, 2025
M
Enable optimized op_le broadcast against 1 element tensor
Manuel Candales committed
March 13, 2025
S
Fix missing buck dep for op_where (#9229)
Scott Wolchok committed
March 6, 2025
S
Add optimized op_where (#8866)
Scott Wolchok committed
February 25, 2025
P
Clean up optimized-oss.yaml (#8668)
pytorchbot committed
February 21, 2025
K
[Executorch] Add broadcasting support to optimized op_sub (#8256)
Kimish Patel committed
February 19, 2025
P
Use at::Vectorized in optimized log_softmax
pytorchbot committed
February 18, 2025
K
[Executorch] Refactor op_add to support op_sub broadcasting (#8255)
Kimish Patel committed
February 14, 2025
S
Fix shadowing of C <complex.h> by c10 include directory
Scott Wolchok committed
February 13, 2025
P
Add -Wno-global-constructors -Wno-shadow to fft_r2c op target (#8452)
pytorchbot committed
February 12, 2025
P
Reuse GELU implementation from PyTorch core (#8322)
pytorchbot committed
February 7, 2025
S
Implement _fft_r2c core ATen op (#8277)
Scott Wolchok committed
January 28, 2025
S
unbreak optimized gelu test (#7987)
Scott Wolchok committed
November 18, 2024
H
[Executorch] optimized sigmoid
Hansong committed
October 31, 2024
P
[Executorch] Handle broadcast semantics for last dim (#6602)
pytorchbot committed
September 11, 2024
S
Add optimized op_linear (#5243)
Scott Wolchok committed
S
Optimized op_mm using CPUBlas gemm (#5242)
Scott Wolchok committed
August 29, 2024
March 22, 2024
G
Build optimized library with CMake (#2530)
Gregory Comer committed
December 5, 2023
H
Enable sleef, BLAS for executor_runner_optimized (#1354)
Hansong Zhang committed
October 11, 2023
M
Fix & cleanup optimized native_layer_norm (#812)
Manuel Candales committed
October 10, 2023
M
Fix optimized log_softmax (#792)
Manuel Candales committed
July 31, 2023
F
Initial commit
facebook-github-bot committed