.. |
kernels
|
Fused GEMM (#1123)
|
2024-05-15 10:30:41 -07:00 |
mps
|
copyright + ack
|
2023-11-30 11:12:53 -08:00 |
allocator.cpp
|
Reset peak memory (#1074)
|
2024-05-03 17:12:51 -07:00 |
allocator.h
|
Reset peak memory (#1074)
|
2024-05-03 17:12:51 -07:00 |
CMakeLists.txt
|
Shared events for synchronization + async eval (#998)
|
2024-04-17 06:16:02 -07:00 |
compiled_preamble.h
|
Kernel generation (#614)
|
2024-02-07 13:15:59 -08:00 |
compiled.cpp
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
conv.cpp
|
Conv3d (#993)
|
2024-05-11 06:15:02 -07:00 |
copy.cpp
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
copy.h
|
Add a SliceUpdate op and primitive (#850)
|
2024-03-20 10:39:25 -07:00 |
device.cpp
|
Fused GEMM (#1123)
|
2024-05-15 10:30:41 -07:00 |
device.h
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
event.cpp
|
Shared events for synchronization + async eval (#998)
|
2024-04-17 06:16:02 -07:00 |
fft.cpp
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
indexing.cpp
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
make_compiled_preamble.sh
|
quote file name (#670)
|
2024-02-11 10:33:30 -08:00 |
matmul.cpp
|
Fused GEMM (#1123)
|
2024-05-15 10:30:41 -07:00 |
matmul.h
|
Add groups to Conv1d (#948)
|
2024-04-27 06:24:57 -07:00 |
metal_impl.h
|
Add synchronize function (#1006)
|
2024-04-22 08:25:46 -07:00 |
metal.cpp
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
metal.h
|
Reset peak memory (#1074)
|
2024-05-03 17:12:51 -07:00 |
normalization.cpp
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
primitives.cpp
|
Add conjugate operator (#1100)
|
2024-05-10 07:22:20 -07:00 |
quantized.cpp
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
reduce.cpp
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
reduce.h
|
Explicit barriers with concurrent dispatch (#977)
|
2024-04-10 21:45:31 -07:00 |
rope.cpp
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
scaled_dot_product_attention.cpp
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
scan.cpp
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
softmax.cpp
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
sort.cpp
|
Split encoders in non-concurrent context with a max ops per encoder (#1085)
|
2024-05-09 16:21:02 -07:00 |
utils.h
|
Metal FFT for powers of 2 up to 2048 (#915)
|
2024-04-11 21:40:06 -07:00 |