saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-24 19:43:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/js/web/lib/wasm/jsep/webgpu/ops
History
Yang Gu 53de2d8cb0
[js/webgpu] Enable GroupedConvVectorize path (#19791) 
Vectorize met 2 failed cases in a CI bot with NVIDIA GPU, but we
couldn't repro with all the GPUs at hand, including NVIDIA GPUs. This PR
introduces GPUAdapterInfo and enables this opt on non-NVIDIA GPUs to
make the bots happy.
No obivous perf gain can be seen if we enable vectorize on NVIDIA.
However, it shows big perf improvement on Intel. On my Gen12 Intel GPU,
mobilenetv2-12 perf was improved from 11.14ms to 7.1ms.
2024-03-12 22:25:07 -07:00
..
3rd-party [js/webgpu] Fix Conv2DTransposeMatMul f16 compilation failure (#19596) 2024-02-22 13:09:28 -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] Use DataType as uniform cpu type (#19281) 2024-01-30 21:05:08 -08:00
batch-norm.ts [js/webgpu] Use DataType as uniform cpu type (#19281) 2024-01-30 21:05:08 -08:00
bias-add.ts [js/webgpu] revise uniform support (#17871) 2023-10-11 16:41:46 -07:00
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] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
concat.ts [JS/WebGPU] Preserve zero size input tensor dims. (#19737) 2024-03-07 19:07:49 -08:00
conv-grouped.ts [js/webgpu] Add LeakyRelu activation for fusedConv (#19369) 2024-02-02 09:06:38 -08:00
conv-transpose.ts [js/webgpu] Support uniforms for conv, conv transpose, conv grouped (#18753) 2024-01-25 15:37:05 -08:00
conv.ts [js/webgpu] Enable GroupedConvVectorize path (#19791) 2024-03-12 22:25:07 -07:00
cumsum.ts [js/webgpu] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
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 LeakyRelu activation for fusedConv (#19369) 2024-02-02 09:06:38 -08:00
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
instance-norm.ts [js/webgpu] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
layer-norm.ts [js] small fix to workaround formatter (#19400) 2024-02-20 17:23:01 -08:00
matmul.ts [js/webgpu] Add LeakyRelu activation for fusedConv (#19369) 2024-02-02 09:06:38 -08:00
matmulnbits.ts [JS/WebGPU] Add MatMulNBits (#19446) 2024-02-17 09:19:17 -08:00
multi-head-attentiion.ts [js/webgpu] Use DataType as uniform cpu type (#19281) 2024-01-30 21:05:08 -08:00
pad.ts [js/webgpu] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
pool.ts [js/webgpu] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
range.ts [js/webgpu] Use DataType as uniform cpu type (#19281) 2024-01-30 21:05:08 -08:00
reduce-shared.ts [js/webgpu] Use DataType as uniform cpu type (#19281) 2024-01-30 21:05:08 -08:00
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
skip-layer-norm.ts [js/webgpu] Use DataType as uniform cpu type (#19281) 2024-01-30 21:05:08 -08:00
slice.ts [js/webgpu] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
softmax.ts [js/webgpu] Use DataType as uniform cpu type (#19281) 2024-01-30 21:05:08 -08:00
split.ts [js/webgpu] Create Split indices helpers by rank, not by shape (#19554) 2024-02-20 09:24:34 -08:00
tile.ts [js/webgpu] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
transpose.ts [js/webgpu] Refactor createTensorShapeVariables (#18883) 2024-02-01 17:59:00 -08:00
unary-op.ts [js/webgpu] support customop FastGelu (#19392) 2024-02-06 09:07:31 -08:00
where.ts [JS/WebGPU] Fix Split and Where to handle corner cases. (#19613) 2024-02-23 00:21:15 -08:00