COMMITS
/ kernels/optimized/cpu/op_mul.cpp May 1, 2025
T
Add complex dtype support to mul
Tarun Karuturi committed
February 13, 2025
K
[Executorch] Refactor op_mul's broadcasting utils (#8204)
Kimish Patel committed
January 28, 2025
S
Execute on exec_aten namespace deprecation from #5296 (#7950)
Scott Wolchok committed
October 31, 2024
P
[Executorch] Handle broadcast semantics for last dim (#6602)
pytorchbot committed
P
[Executorch] mul broadcast update (#6589)
pytorchbot committed
September 12, 2024
D
Migrate RuntimeContext users to KernelRuntimeContext (#5270)
Dave Bort committed
September 8, 2024
S
[ExecuTorch] Handle rank 0 tensors correctly in optimized add/sub/div/mul
Scott Wolchok committed
September 5, 2024
S
[ExecuTorch] support BF16 in op_mul
Scott Wolchok committed
August 29, 2024
May 9, 2024
S
Use compile-time promotion to reduce optimized mul op size & build time (#3532)
Scott Wolchok committed
March 21, 2024
K
Make RoPE freq calculation broadcast for per head (#2353)
Kimish Patel committed
March 13, 2024
G
Update kernels for non-fatal (part 11) (#2120)
Gregory Comer committed
January 27, 2024
M
Half to float only after checking common type equals output type for scalar variants (#1732)
Manuel Candales committed
January 26, 2024
M
Half support: mul (#1704)
Manuel Candales committed
January 11, 2024
G
Refactor resize_to_broadcast_target_size for non-fatal (#1558)
Gregory Comer committed
October 25, 2023
L
Update optimized op names to match optimized.yaml (#1091)
Lucy Qiu committed
July 31, 2023
F
Initial commit
facebook-github-bot committed