saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-23 19:32:23 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/js/web/lib/wasm/jsep/webgpu/ops
History
Jiajia Qin fd6bab4250
[js/webgpu] Provide a vectorized algorithm for GroupedConv (#18884) 
### Description
This PR provides a vectorized algorithm for NHWC GroupedConv to improve
performance.

The aggregate time of GroupedConv in mobilenetv2-12 becomes ~1ms from
~4ms on Intel Alder Lake machine. About 20% improvement for the whole
model.
2024-01-10 16:12:43 -08:00
..
3rd-party [js/webgpu] Fix f16 errors for ConvTranspose2D (#18986) 2024-01-04 08:06:01 -08:00
argminmax.ts [JS/Web] Added uniforms to Reduce, Resize and Split Ops. (#18727) 2023-12-12 11:12:23 -08:00
attention.ts [js/webgpu] Support uniforms for attention and multihead attention (#18903) 2024-01-09 07:46:30 -08:00
batch-norm.ts
bias-add.ts
bias-split-gelu.ts
binary-op.ts
common.ts [js/webgpu] Support uniforms for attention and multihead attention (#18903) 2024-01-09 07:46:30 -08:00
concat.ts
conv-grouped.ts [js/webgpu] Provide a vectorized algorithm for GroupedConv (#18884) 2024-01-10 16:12:43 -08:00
conv-transpose.ts [js/webgpu] Use the naive convTranspose when in/out channels are both 1 (#18658) 2023-12-04 13:18:37 -08:00
conv.ts [js/webgpu] Provide a vectorized algorithm for GroupedConv (#18884) 2024-01-10 16:12:43 -08:00
cumsum.ts [JS/Web] Added uniforms to Reduce, Resize and Split Ops. (#18727) 2023-12-12 11:12:23 -08:00
einsum.ts
expand.ts [js/webgpu] Fix Expand/Gather when input type is bool (#18999) 2024-01-05 08:16:15 -08:00
fuse-utils.ts
gather-elements.ts [JS/Web] AddedUniforms in GatherElements. (#18670) 2023-12-05 09:19:53 -08:00
gather.ts [js/webgpu] Fix Expand/Gather when input type is bool (#18999) 2024-01-05 08:16:15 -08:00
gemm.ts [js/webgpu] Support gemm uniforms (#19056) 2024-01-09 09:57:06 -08:00
instance-norm.ts [js/webgpu] Support uniforms for instance-norm (#18929) 2024-01-09 14:56:00 -08:00
layer-norm.ts [js/webgpu] Support uniforms for layer-norm (#18755) 2024-01-08 18:16:25 -08:00
matmul.ts [js/webgpu] Provide a naive vectorized matmul algorithm (#18758) 2023-12-13 09:03:23 -08:00
multi-head-attentiion.ts [js/webgpu] Support uniforms for attention and multihead attention (#18903) 2024-01-09 07:46:30 -08:00
pad.ts [js/webgpu] Support pad uniforms (#19057) 2024-01-09 09:34:56 -08:00
pool.ts [js/webgpu] Refactor attributes of pool (#18728) 2023-12-26 17:23:52 -08:00
range.ts [js/webgpu] Support range uniforms (#19055) 2024-01-09 09:33:57 -08:00
reduce-shared.ts [JS/WebGPU] fix an error in Clip (#18799) 2023-12-19 13:51:01 -08:00
reduce.ts [JS/Web] Added uniforms to Reduce, Resize and Split Ops. (#18727) 2023-12-12 11:12:23 -08:00
resize.ts [js/webgpu] Mitigate floating point accuracy issue in Resize (#18956) 2024-01-03 14:15:26 -08:00
skip-layer-norm.ts
slice.ts [JS/Web] Added uniforms to Reduce, Resize and Split Ops. (#18727) 2023-12-12 11:12:23 -08:00
softmax.ts [JS/WebGPU] fix an error in Clip (#18799) 2023-12-19 13:51:01 -08:00
split.ts [JS/Web] Added uniforms to Reduce, Resize and Split Ops. (#18727) 2023-12-12 11:12:23 -08:00
tile.ts [JS/WebGPU] Added uniforms to Tile and Where Ops (#18768) 2023-12-11 20:58:52 -08:00
transpose.ts
unary-op.ts [JS/WebGPU] fix an error in Clip (#18799) 2023-12-19 13:51:01 -08:00
where.ts [JS/WebGPU] Added uniforms to Tile and Where Ops (#18768) 2023-12-11 20:58:52 -08:00