saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-28 20:11:22 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/js/web/lib/wasm/jsep/webgpu/ops
History
xhcao 9c6ee89fa7
[js/webgpu] fix two errors of attention operator (#21687) 
Fix two issues:
(1) scale shall be fp32 instead of f16
(2) Softmax program does not handle the normalized dispatch group values, so if the sequence length is over 65535, the result is not correct for this program.
2024-08-13 09:42:34 -07:00
..
3rd-party [js/webgpu] Add activation for conv3d naive (#21466) 2024-07-29 08:47:41 -07:00
argminmax.ts
attention.ts [js/webgpu] fix two errors of attention operator (#21687) 2024-08-13 09:42:34 -07:00
batch-norm.ts [js/webgpu] Use DataType as uniform cpu type (#19281) 2024-01-30 21:05:08 -08:00
bias-add.ts
bias-split-gelu.ts [js/webgpu] support customop FastGelu (#19392) 2024-02-06 09:07:31 -08:00
binary-op.ts [js/webgpu] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
common.ts [js/webgpu] fixes for fp16 attention (#20440) 2024-04-24 08:01:28 -07:00
concat.ts Eliminate explicit Concat operations in Attention (#20556) 2024-05-24 09:07:57 -07:00
conv-grouped.ts [js/webgpu] perform uniform consistency check (#20019) 2024-03-26 17:14:43 -07:00
conv-transpose.ts fix ConvTranspose 1D (#20194) 2024-04-05 10:05:32 -07:00
conv.ts [js/webgpu] Support conv3d naive (#20706) 2024-06-19 10:13:50 -07:00
cumsum.ts fix csum and enable ut (#20355) 2024-04-17 15:01:06 -07:00
depth-to-space.ts [js/webgpu] implement DepthToSpace operator in webgpu (#19948) 2024-04-10 12:13:46 -07:00
einsum.ts [js/webgpu] Use DataType as uniform cpu type (#19281) 2024-01-30 21:05:08 -08:00
expand.ts [js/webgpu] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
fast-gelu.ts [js/webgpu] support customop FastGelu (#19392) 2024-02-06 09:07:31 -08:00
fuse-utils.ts [js/webgpu] Add activation Tanh (#21540) 2024-07-29 11:05:34 -07:00
gather-elements.ts [js/webgpu] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
gather.ts [js/webgpu] minor fixes to make tinyllama work (#19564) 2024-02-23 15:45:30 -08:00
gemm.ts [js/webgpu] Use DataType as uniform cpu type (#19281) 2024-01-30 21:05:08 -08:00
group-query-attention.ts [js/webgpu] Fix mha name (#20860) 2024-05-30 00:01:06 -07:00
instance-norm.ts [js/webgpu] Use global id in attention and instance-norm (#20008) 2024-04-02 01:42:39 -07:00
layer-norm.ts [js/web] support SimplifiedLayerNorm and SkipSimplifiedLayerNorm (#20277) 2024-04-11 14:08:50 -07:00
matmul.ts [js/webgpu] Add LeakyRelu activation for fusedConv (#19369) 2024-02-02 09:06:38 -08:00
matmulnbits.ts [JS/WebGPU] MatMulNBits remove unnecessary condition (#20396) 2024-04-29 14:27:21 -07:00
multihead-attention.ts [js/webgpu] Fix mha name (#20860) 2024-05-30 00:01:06 -07:00
pad.ts [js/webgpu] perform uniform consistency check (#20019) 2024-03-26 17:14:43 -07:00
pool.ts [js/webgpu] fix maxpool / fp16 (#19981) 2024-03-19 16:15:49 -07:00
quantize-linear.ts [JS/WebGPU] Add Dequantizelinear operator (#21642) 2024-08-09 14:44:19 -07:00
range.ts [js/webgpu] Use DataType as uniform cpu type (#19281) 2024-01-30 21:05:08 -08:00
reduce-shared.ts accumulate in fp32 for Reduce* (#19868) 2024-03-18 08:28:43 -07:00
reduce.ts [js/webgpu] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
resize.ts [js/webgpu] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
rotary-embedding.ts [js/webgpu] Implement com.microsoft.RotaryEmbedding (#20209) 2024-04-08 09:11:26 -07:00
skip-layer-norm.ts optimize skiplayernorm (#20551) 2024-05-08 08:40:03 -07:00
slice.ts [js/webgpu] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
softmax.ts [js/webgpu] perform uniform consistency check (#20019) 2024-03-26 17:14:43 -07:00
split.ts [js/webgpu] Create Split indices helpers by rank, not by shape (#19554) 2024-02-20 09:24:34 -08:00
tile.ts add missing file for pr20791 (#20811) 2024-05-24 09:59:13 -07:00
transpose.ts [js/webgpu] Support shared memory for transpose 2d (#19267) 2024-05-22 08:15:44 -07:00
unary-op.ts webgpu quickgelu (#20939) 2024-06-06 08:21:33 -07:00
where.ts [JS/WebGPU] Fix Split and Where to handle corner cases. (#19613) 2024-02-23 00:21:15 -08:00