Angelos Katharopoulos 8590c0941e Add load_safe to the general conv loaders (#2258)

2025-06-10 20:58:16 -07:00

..

fft

Fix fft for integer overflow (#2161)

2025-05-09 14:25:12 -07:00

jit

Dispatch bf16 at run time when using the JIT (#1584)

2024-11-15 16:54:36 -08:00

metal_3_0

Dispatch bf16 at run time when using the JIT (#1584)

2024-11-15 16:54:36 -08:00

metal_3_1

Dispatch bf16 at run time when using the JIT (#1584)

2024-11-15 16:54:36 -08:00

reduction

Fix typo in row_reduce_small (#2179)

2025-05-13 20:19:54 -07:00

steel

Add load_safe to the general conv loaders (#2258)

2025-06-10 20:58:16 -07:00

arange.h

More jitting (#1132)

2024-05-23 16:23:44 -07:00

arange.metal

Custom logsumexp (#2028)

2025-03-31 07:36:55 -07:00

arg_reduce.metal

fix large arg reduce (#2206)

2025-05-19 13:10:44 -07:00

atomic.h

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

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

bf16_math.h

Dispatch bf16 at run time when using the JIT (#1584)

2024-11-15 16:54:36 -08:00

binary_ops.h

Complex scan (#2094)

2025-04-22 18:56:28 -07:00

binary_two.h

Improve metal elementwise kernels (#2247)

2025-06-06 11:37:40 -07:00

binary_two.metal

Improve metal elementwise kernels (#2247)

2025-06-06 11:37:40 -07:00

binary.h

Improve metal elementwise kernels (#2247)

2025-06-06 11:37:40 -07:00

binary.metal

Improve metal elementwise kernels (#2247)

2025-06-06 11:37:40 -07:00

CMakeLists.txt

Gather mm new kernel and small refactoring (#2040)

2025-04-14 16:37:36 -07:00

complex.h

Add more complex unary ops (#2101)

2025-04-21 13:04:54 -07:00

conv.metal

Depthwise Conv2D optimization (#2036)

2025-04-03 09:42:04 -07:00

copy.h

Improve metal elementwise kernels (#2247)

2025-06-06 11:37:40 -07:00

copy.metal

Improve metal elementwise kernels (#2247)

2025-06-06 11:37:40 -07:00

defines.h

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

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

erf.h

JIT compile option for binary minimization (#1091)

2024-05-22 12:57:13 -07:00

expm1f.h

Fix overflow / underflow handling for expm1f (#1278)

2024-07-23 07:29:06 -07:00

fence.metal

Faster synchronization Fence primitive (#1773)

2025-01-17 18:42:19 -08:00

fft.h

fix fft bug (#2062)

2025-04-10 19:41:27 -07:00

fft.metal

Add Quantized Ops to the JIT (#1204)

2024-06-12 09:47:12 -07:00

gather_axis.h

scatter axis + gather axis primitives (#1813)

2025-01-31 20:48:08 -08:00

gather.h

Use int64 stride everywhere (#1671)

2024-12-09 11:09:02 -08:00

gemv_masked.h

Use same accumulation precision in gemv as gemm (#1962)

2025-03-16 07:13:24 -07:00

gemv_masked.metal

Use int64 stride everywhere (#1671)

2024-12-09 11:09:02 -08:00

gemv.metal

enable complex gemm (#2017)

2025-03-28 10:45:13 -07:00

hadamard.h

GPU Hadamard for large N (#1879)

2025-05-01 17:19:17 -07:00

indexing.h

Use int64 stride everywhere (#1671)

2024-12-09 11:09:02 -08:00

layer_norm.metal

Change layernorms to two pass algorithm (#2246)

2025-06-06 13:34:56 -07:00

logsumexp.h

Fix out-of-bounds default value in logsumexp/softmax (#2213)

2025-05-21 07:25:16 -07:00

logsumexp.metal

Custom logsumexp (#2028)

2025-03-31 07:36:55 -07:00

quantized.h

5bit quants (#2226)

2025-05-30 12:12:10 -07:00

quantized.metal

5bit quants (#2226)

2025-05-30 12:12:10 -07:00

random.metal

Use int64 stride everywhere (#1671)

2024-12-09 11:09:02 -08:00

reduce_utils.h

More jitting (#1132)

2024-05-23 16:23:44 -07:00

reduce.h

Fix JIT reductions (#1373)

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

reduce.metal

Allow no copy negative strides in as_strided and slice (#1688)

2024-12-12 08:59:45 -08:00

rms_norm.metal

Custom logsumexp (#2028)

2025-03-31 07:36:55 -07:00

rope.metal

Dispatch bf16 at run time when using the JIT (#1584)

2024-11-15 16:54:36 -08:00

scaled_dot_product_attention.metal

Add float mask to sdpa vector (#2068)

2025-04-11 17:29:40 -07:00

scan.h

LogCumSumExp (#2069)

2025-04-13 01:27:29 -07:00

scan.metal

Complex scan (#2094)

2025-04-22 18:56:28 -07:00

scatter_axis.h

scatter axis + gather axis primitives (#1813)

2025-01-31 20:48:08 -08:00

scatter.h

Use int64 stride everywhere (#1671)

2024-12-09 11:09:02 -08:00

sdpa_vector.h

fix batched vector sdpa (#2152)

2025-05-05 13:13:03 -07:00

softmax.h

Fix out-of-bounds default value in logsumexp/softmax (#2213)

2025-05-21 07:25:16 -07:00

softmax.metal

Custom logsumexp (#2028)

2025-03-31 07:36:55 -07:00

sort.h

faster sort (#1831)

2025-02-05 06:10:22 -08:00

sort.metal

faster sort (#1831)

2025-02-05 06:10:22 -08:00

ternary_ops.h

JIT compile option for binary minimization (#1091)

2024-05-22 12:57:13 -07:00

ternary.h

Improve metal elementwise kernels (#2247)

2025-06-06 11:37:40 -07:00

ternary.metal

Improve metal elementwise kernels (#2247)

2025-06-06 11:37:40 -07:00

unary_ops.h

Add more complex unary ops (#2101)

2025-04-21 13:04:54 -07:00

unary.h

Improve metal elementwise kernels (#2247)

2025-06-06 11:37:40 -07:00

unary.metal

Improve metal elementwise kernels (#2247)

2025-06-06 11:37:40 -07:00

utils.h

fix bw for elementwise ops (#2151)

2025-05-05 06:15:04 -07:00