| .. |
|
jit
|
Option to JIT steel gemm / conv (#1139)
|
2024-05-23 18:07:34 -07:00 |
|
kernels
|
Fix a couple bugs (#1161)
|
2024-05-28 15:18:18 -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 |
|
binary.cpp
|
JIT compile option for binary minimization (#1091)
|
2024-05-22 12:57:13 -07:00 |
|
CMakeLists.txt
|
Option to JIT steel gemm / conv (#1139)
|
2024-05-23 18:07:34 -07:00 |
|
compiled.cpp
|
Fix a couple bugs (#1161)
|
2024-05-28 15:18:18 -07:00 |
|
conv.cpp
|
Option to JIT steel gemm / conv (#1139)
|
2024-05-23 18:07:34 -07:00 |
|
copy.cpp
|
JIT compile option for binary minimization (#1091)
|
2024-05-22 12:57:13 -07:00 |
|
copy.h
|
Add a SliceUpdate op and primitive (#850)
|
2024-03-20 10:39:25 -07:00 |
|
device.cpp
|
JIT compile option for binary minimization (#1091)
|
2024-05-22 12:57:13 -07:00 |
|
device.h
|
Fix offset bug for device buffers (#1151)
|
2024-05-22 15:50:05 -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
|
More jitting (#1132)
|
2024-05-23 16:23:44 -07:00 |
|
jit_kernels.cpp
|
Fix a couple bugs (#1161)
|
2024-05-28 15:18:18 -07:00 |
|
kernels.h
|
Fix a couple bugs (#1161)
|
2024-05-28 15:18:18 -07:00 |
|
make_compiled_preamble.sh
|
Option to JIT steel gemm / conv (#1139)
|
2024-05-23 18:07:34 -07:00 |
|
matmul.cpp
|
Fix matvec vector stride bug (#1168)
|
2024-05-29 12:18:28 -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 |
|
nojit_kernels.cpp
|
Fix a couple bugs (#1161)
|
2024-05-28 15:18:18 -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
|
More jitting (#1132)
|
2024-05-23 16:23:44 -07:00 |
|
quantized.cpp
|
Rename block sparse (#1149)
|
2024-05-22 07:48:34 -07:00 |
|
reduce.cpp
|
Fix a couple bugs (#1161)
|
2024-05-28 15:18:18 -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
|
More jitting (#1132)
|
2024-05-23 16:23:44 -07:00 |
|
softmax.cpp
|
More jitting (#1132)
|
2024-05-23 16:23:44 -07:00 |
|
sort.cpp
|
More jitting (#1132)
|
2024-05-23 16:23:44 -07:00 |
|
ternary.cpp
|
JIT compile option for binary minimization (#1091)
|
2024-05-22 12:57:13 -07:00 |
|
unary.cpp
|
JIT compile option for binary minimization (#1091)
|
2024-05-22 12:57:13 -07:00 |
|
utils.h
|
Metal FFT for powers of 2 up to 2048 (#915)
|
2024-04-11 21:40:06 -07:00 |
