jzm-intel d9b91682f1 WebGPU JSEP: Make shader code not depend on input broadcasting patterns (#22536) ... This PR make MatMul shaders not depend on inputs broadcasting pattern, but only depend on input ranks and their shape provided in uniform. This change fix the issue that currently shaders code are different for different broadcasting, but have identical cache key and results in wrong cache hit.		2024-11-08 11:00:51 -08:00
..
_example.jsonc
abs-int32.jsonc
abs.jsonc
absr.jsonc
abss.jsonc
acos.jsonc
add.jsonc	[js/web] fix suite test list for zero sized tensor (#19638)	2024-02-24 10:09:07 -08:00
add_int32.jsonc
add_zero-sized.jsonc	[js/web] fix suite test list for zero sized tensor (#19638)	2024-02-24 10:09:07 -08:00
and.jsonc
asin.jsonc
attention.jsonc
batch-norm.jsonc
bias-add.jsonc
bias-split-gelu.jsonc
cast.jsonc
ceil.jsonc
clip.jsonc	[js/webgpu] support float16 for Clip (#21584)	2024-08-28 13:19:20 -07:00
concat.jsonc
concat_int32.jsonc
concat_zero-sized.jsonc	[JS/WebGPU] Preserve zero size input tensor dims. (#19737)	2024-03-07 19:07:49 -08:00
conv-transpose.jsonc	[JS/WebGPU] Use non-matmul implementation for ConvTranspose in channel-first case. (#20022)	2024-03-23 11:19:14 -07:00
conv.jsonc	[js/webgpu] Optimize grouped conv (#21892)	2024-09-04 17:16:35 -07:00
conv1d.jsonc	[js/webgpu] Optimize conv1d by conv2d (#19388)	2024-08-22 22:56:07 -07:00
conv3dncdhw.jsonc	[js/webgpu] Support conv3d naive (#20706)	2024-06-19 10:13:50 -07:00
cos.jsonc
cumsum.jsonc
depth-to-space.jsonc
dequantize-linear-int4.jsonc	[JS/WebGPU] Add GatherBlockQuantized op support (#21734)	2024-08-26 14:46:04 -07:00
dequantizelinear.jsonc	[JS/WebGPU] Add Dequantizelinear operator (#21642)	2024-08-09 14:44:19 -07:00
div.jsonc
div_int32.jsonc
einsum.jsonc
equal.jsonc
exp.jsonc
expand.jsonc
fast-gelu.jsonc	[js/webgpu] support customop FastGelu (#19392)	2024-02-06 09:07:31 -08:00
floor.jsonc
fused-conv.jsonc	[js/webgpu] Add activation Tanh (#21540)	2024-07-29 11:05:34 -07:00
fused-conv3dncdhw.jsonc	[js/webgpu] Add activation for conv3d naive (#21466)	2024-07-29 08:47:41 -07:00
gather-block-quantized.jsonc	[JS/WebGPU] Add GatherBlockQuantized op support (#21734)	2024-08-26 14:46:04 -07:00
gather-elements.jsonc
gather.jsonc
gelu.jsonc
gemm.jsonc
global-average-pool.jsonc
greater.jsonc
group-query-attention.jsonc	[JSEP/WebGPU] Fix data causing output mismatch resulting in CI build failures occasionally (#22596)	2024-10-26 01:37:12 -07:00
identity.jsonc
image-scaler.jsonc
instance-norm.jsonc	[js/webgpu] Fix NAN caused by un-initialized buffer in instance-norm (#19387)	2024-03-18 22:59:32 -07:00
layer-norm.jsonc
leaky-relu.jsonc
less.jsonc
log.jsonc
matmul-broadcast.jsonc
matmul.jsonc	WebGPU JSEP: Make shader code not depend on input broadcasting patterns (#22536)	2024-11-08 11:00:51 -08:00
matmulnbits.jsonc	[JS/WebGPU] Improve MatMulNBits perf (#19974)	2024-04-12 11:03:05 -07:00
max-pool.jsonc	[js/webgpu] Fix max pool shape end with 0 (#21698)	2024-08-13 20:59:24 -07:00
mul.jsonc
mul_int32.jsonc
multihead-attention.jsonc	[JS/WebGPU] Avoid producing presentKey/presentValue outputs if pastKey/pastValue … (#21782)	2024-08-19 18:02:19 -07:00
neg-int32.jsonc
neg.jsonc
not.jsonc
or.jsonc
pad-big.jsonc
pad.jsonc
pad_f16.jsonc	[js/webgpu] Enable pad f16 uniform (#21691)	2024-08-26 07:58:48 -07:00
pow-big-number.jsonc
pow.jsonc
pow_int32.jsonc
quick-gelu.jsonc	webgpu quickgelu (#20939)	2024-06-06 08:21:33 -07:00
reduce-min.jsonc
relu.jsonc
reshape-int32.jsonc
reshape-pack.jsonc
reshape.jsonc
resize-pack.jsonc
resize.jsonc
rotary-embedding.jsonc	[js/webgpu] Implement com.microsoft.RotaryEmbedding (#20209)	2024-04-08 09:11:26 -07:00
shape.jsonc
simplified-layer-norm.jsonc	[js/web] fix test runner with optional input/output (#20399)	2024-04-22 12:53:10 -07:00
sin.jsonc
skip-layer-norm.jsonc	[js/web] fix test runner with optional input/output (#20399)	2024-04-22 12:53:10 -07:00
skip-simplified-layer-norm.jsonc	[js/web] fix test runner with optional input/output (#20399)	2024-04-22 12:53:10 -07:00
slice.jsonc
softmax.jsonc	[js/webgpu] Remove the limitation on axis in softmax (#22231)	2024-09-30 18:27:11 -07:00
split.jsonc	[js/webgpu] Handle negative axis in op Split (#21771)	2024-08-17 16:41:23 -07:00
sqrt.jsonc
sub.jsonc
sub_int32.jsonc
tan.jsonc
tanh.jsonc	[js/webgpu] Fix Tanh explosion (#19201)	2024-01-25 08:25:35 -08:00
tile.jsonc
transpose.jsonc	[js/webgpu] Optimize transpose (#21964)	2024-09-04 12:04:04 -07:00
transpose_int32_uint32.jsonc
upsample.jsonc
where.jsonc	[JS/WebGPU] Fix Split and Where to handle corner cases. (#19613)	2024-02-23 00:21:15 -08:00
where_broadcast.jsonc
xor.jsonc