Awni Hannun 41c603d48a fix jit reduce (#1395)

2024-09-04 14:03:10 -07:00

..

jit

Fix JIT reductions (#1373)

2024-08-28 16:39:11 -07:00

kernels

fix jit reduce (#1395)

2024-09-04 14:03:10 -07:00

allocator.cpp

Do not release buffers on exit (#1142)

2024-07-15 15:12:24 -07:00

allocator.h

Reset peak memory (#1074)

2024-05-03 17:12:51 -07:00

binary.cpp

Fixes for large arrays with a few ops (#1299)

2024-07-30 17:18:39 -07:00

binary.h

Fixes for large arrays with a few ops (#1299)

2024-07-30 17:18:39 -07:00

CMakeLists.txt

Fix JIT reductions (#1373)

2024-08-28 16:39:11 -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

Fix copy in the sort primitive (#1383)

2024-08-31 08:32:14 -07:00

copy.h

Add a SliceUpdate op and primitive (#850)

2024-03-20 10:39:25 -07:00

custom_kernel.cpp

Add grid_sample example to metal_kernel docs (#1352)

2024-08-23 18:24:16 -07:00

device.cpp

fix extension metal library finding (#1361)

2024-08-26 09:18:50 -07:00

device.h

fix extension metal library finding (#1361)

2024-08-26 09:18:50 -07:00

distributed.cpp

Adds send/recv ops in distributed (#1366)

2024-08-26 23:01:37 -07:00

event.cpp

Shared events for synchronization + async eval (#998)

2024-04-17 06:16:02 -07:00

fft.cpp

Fix contiguity check (#1336)

2024-08-19 16:05:06 -07:00

hadamard.cpp

Fast Hadamard Transform (#1249)

2024-07-09 20:39:01 -07:00

indexing.cpp

2d gather specialization (#1339)

2024-08-22 10:48:24 -07:00

jit_kernels.cpp

fix jit reduce (#1395)

2024-09-04 14:03:10 -07:00

kernels.h

fix jit reduce (#1395)

2024-09-04 14:03:10 -07:00

make_compiled_preamble.sh

fix compiling with space in paths (#1332)

2024-08-15 16:39:24 -07:00

matmul.cpp

Add gemv masked to JIT plus some fixes (#1310)

2024-08-07 13:38:07 -07:00

matmul.h

Add gemv masked to JIT plus some fixes (#1310)

2024-08-07 13:38:07 -07:00

metal_impl.h

Add synchronize function (#1006)

2024-04-22 08:25:46 -07:00

metal.cpp

MPI ops in GPU stream for faster comms (#1356)

2024-08-26 15:12:50 -07:00

metal.h

Reset peak memory (#1074)

2024-05-03 17:12:51 -07:00

nojit_kernels.cpp

fix jit reduce (#1395)

2024-09-04 14:03:10 -07:00

normalization.cpp

Refactor reductions and fix scatter atomics for large sizes (#1300)

2024-08-22 16:03:31 -07:00

primitives.cpp

Even Even Faster IO (#1374)

2024-08-29 16:05:40 -07:00

quantized.cpp

Fix overflow in quantize/dequantize (#1379)

2024-08-30 13:32:41 -07:00

reduce.cpp

fix jit reduce (#1395)

2024-09-04 14:03:10 -07:00

reduce.h

Further reduction tuning (#1349)

2024-08-23 10:35:25 -07:00

rope.cpp

Fix rope (#1340)

2024-08-20 17:37:52 -07:00

scaled_dot_product_attention.cpp

Metal shaders for memory efficient self attention on large sequences (#964)

2024-06-03 09:16:19 -07:00

scan.cpp

fix jit scan when output doesn't have primitive (#1190)

2024-06-06 07:24:58 -07:00

slicing.cpp

Add some internal GPU apis (#1177)

2024-06-04 09:24:26 -07:00

slicing.h

Add some internal GPU apis (#1177)

2024-06-04 09:24:26 -07:00

softmax.cpp

Fixes for large arrays with a few ops (#1299)

2024-07-30 17:18:39 -07:00

sort.cpp

Fix copy in the sort primitive (#1383)

2024-08-31 08:32:14 -07:00

ternary.cpp

Fix ternary for large arrays (#1359)

2024-08-26 11:22:27 -07:00

ternary.h

Add some internal GPU apis (#1177)

2024-06-04 09:24:26 -07:00

unary.cpp

Fixes for large arrays with a few ops (#1299)

2024-07-30 17:18:39 -07:00

unary.h

Add some internal GPU apis (#1177)

2024-06-04 09:24:26 -07:00

utils.cpp

Add gemv masked to JIT plus some fixes (#1310)

2024-08-07 13:38:07 -07:00

utils.h

Add gemv masked to JIT plus some fixes (#1310)

2024-08-07 13:38:07 -07:00