### Description
This PR introduces support for registering external data inside WebNN
EP.
### Motivation and Context
- The WebNN EP needs to register the initializers at graph compilation
stage, for initializers from external data, it can't leverage the
general external data loader framework because the graph compilation of
WebNN EP is executed before external data loader called.
- Exposes the `utils::GetExternalDataInfo`, it is useful for WebNN EP to
read the external tensor's infomation.
- Define a new `registerMLConstant` in JSEP to create WebNN constants
from external data in WebNN backend, with the info of tensor as
parameters, as well as the `Module.MountedFiles`, which holds all
preloaded external files.
### Description
This change enables caching `MLTensor`s between inferences runs. This is
done by keeping a reference to `MLTensor`s alive after they have been
released. `MLTensor`s are only destroyed once the sessions goes out of
scope.
### Motivation and Context
Creating and destroying `MTensor`s on every run has a non-trivial
performance penalty. This performance penalty materializes when using
`ort.Tensors`[location=cpu] for inputs/outputs or when using the CPU EP
as a fallback EP for unsupported operators. The former could be
mitigated by developer using `ort.Tensors`[location=ml-tensor]. The
latter cannot be mitigated by developers.
### Description
<!-- Describe your changes. -->
This PR further optimizes matmulnbits specially for iGPUs. The phi3 demo
becomes ~12 tokens/second from ~8 tokens on iGPUs.
Some todos:
1. Make the optimization more general, Remove the blockSize = 32
limitation.
2. Tune the parameter, such as workgroupSize, components size (currently
only support components = 1), to see the performance change.
### Description
<!-- Describe your changes. -->
With this optimization, 96 MultiHeadAttention|Transpose ops in phi3
disappear. Phi3 becomes 113 tokens from 107 tokens on my dGPUs.
The optimization mainly skips the transpose op if one of the transposed
dims is 1. Reshape is enough.
In current implementation, axis in softmax has to be the last, which is
an obvious limitation. This PR removes this limitation and will fix
issues #20710 and #22176.
### Description
Enables using the MLTensor to pass data between models.
### Motivation and Context
Using MLTensor instead of ArrayBuffers reduces the number of copies
between the CPU and devices as well as the renderer and GPU process in
Chromium.
### Description
<!-- Describe your changes. -->
For InstanceNormalization, it has `y = scale * (x - mean) /
sqrt(variance + epsilon) + B` , where mean and variance are computed per
instance per channel. Calculating mean and variance per channel is a
reduce processing, which is NCHW layout friendly since it makes the
adjacent threads can access contiguous data in gpu memory.
This PR optimizes both NHWC and NCHW InstanceNormalization. To
efficiently calculate the mean and variance, we need to make sure the
input is NCHW instead of NHWC. Then use shared memory to do the reduce
operation to get `channel_scale` and `channel_shift`.
With this PR, getting `channel_scale` and `channel_shift` are same for
NHWC and NCHW InstanceNormalization. And the overall performance becomes
very close now.
Below data comes from SD Turbo profiling results.
Before (InstanceNormalization overall time: 140.84 ms)
InstanceNormalization\|InstanceNormComputeMean | 129.70
-- | --
InstanceNormalization\|InstanceNormalizationNHWC | 10.55
InstanceNormalization\|InstanceNormComputeChannelScaleShift | 0.59
After (InstanceNormalization overall time: 59.44 ms)
InstanceNormalization\|InstanceNormComputeChannelScaleShift | 28.57
-- | --
InstanceNormalization\|TransposeShared | 20.19
InstanceNormalization\|InstanceNormalizationNHWC | 10.68
Perf test data(100000 times)
Array: 12.599999997764826ms
String: 1.6000000014901161ms
Perf test case:
```
const permFunctionBodyArray = (rank: number, input: string): string => {
const reverseFunc = [];
reverseFunc.push(`fn perm(i: int) -> int {
var a: int};`);
for (let i = 0; i < rank; ++i) {
reverseFunc.push(input);
}
reverseFunc.push('return a;}');
return reverseFunc.join('\n');
};
const permFunctionBodyString = (rank: number, input: string): string => {
let reverseFunc= `fn perm(i: int}) -> int {
var a: int;`;
for (let i = 0; i < rank; ++i) {
reverseFunc+=input;
}
reverseFunc+='return a;}';
return reverseFunc;//.join('\n');
};
const count = 100000;
let start, end
console.time('array');
start = performance.now();
for(let i =0 ; i < count; i ++) {
permFunctionBodyArray(3, 'input');
}
end = performance.now();
console.timeEnd('array');
console.log("Array: "+ (end-start));
console.time('string');
start = performance.now();
for(let i =0 ; i < count; i ++) {
permFunctionBodyString(3, 'input');
}
end = performance.now();
console.log("String: " +(end-start));
console.timeEnd('string');
```
### Description
<!-- Describe your changes. -->
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
This is to fix issue #22031 to run model demucs.
For conv-transpose, outputPadding.length could be 1, while spatialRank
is 2. The fix is to append enough 0s to outputPadding. For conv, the
issue is similar. kernelShape.length sometimes could be 1, while
inputs[1].dims.length is 4. The fix is also to append enough 0s to
kernelShape.
### Description
<!-- Describe your changes. -->
#21618
This PR optimizes grouped conv by 1) more sequential memory access in
gpu 2) reusing input's data to reduce global memory access times.
See `Conv|GroupedConv` op in
[Wav2Vec2](https://huggingface.co/facebook/wav2vec2-base-960h) becomes
92 ms from 1058 ms on iGPUs with 32 EU.
For the whole model on my iGPUs with 32 EU,
wav2vec2 model becomes 982ms from 1942 ms.
squeezebert-uncased model becomes 71.86ms from 431.77ms.
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
### Description
<!-- Describe your changes. -->
Fix bugs in previous implementation and add more situations to go the
optimized path.
Below situations will go to the optimized path.
1. 2d inputs or squeezed 2d inputs
2. channels last or channels first transpose. For example, channel last
transpose: [1, 256, 512, 512] -> [1, 512, 512, 256]
For this case, the transpose becomes [256, 512x512] -> [512x512, 256]
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
For SD Turbo demo, the total transpose time becomes 39.98ms from
122.09ms. And the correspnding percents becomes 3.89% from 11.05% in
this demo.
This PR will also help #21618, the total transpose time in that demo
becomes 17.32 ms from 70.25 ms on my iGPUs.
### Description
<!-- Describe your changes. -->
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
### Description
<!-- Describe your changes. -->
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
---------
Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com>
### Description
<!-- Describe your changes. -->
See 2x speedup for phi3 on the integrated intel gpu with this
optimization.
The optimization is mainly to store input A's data into local variable
instead of loading them from global memory each time when calculate them
with B data.
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
Avoid producing presentKey/presentValue outputs if pastKey/pastValue
don't exists.
### Description
<!-- Describe your changes. -->
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
### Description
<!-- Describe your changes. -->
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
### Description
<!-- Describe your changes. -->
This PR fixes the `AttentionProbsSoftmax` recompilation issue when
executing the phi3 model. With this fix, it will further improve the
phi3 performance.
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
### Description
Previously, MultiHeadAttention supports relative position bias of shape
[1, N, S, T] or [B, N, S, T], and DecoderMaskedMultiHeadAttention
supports [1, N, S, T]. This will extend the support to allow [1, N, S,
T], [B, N, S, T], [B, 1, S, T] and [1, 1, S, T] for CUDA and CPU EPs.
- [x] Rename the input of "relative position bias" to "attention bias"
because it can also be used for other types of bias, like ALiBi
(Attention with Linear Biases) or attention mask.
- [x] Update unfused kernel to support broadcasting 2nd dimension of
attention bias.
- [x] Update efficient attention to support broadcasting 2nd dimension
of attention bias.
- [x] Update operators (MultiHeadAttention,
DecoderMaskedMultiHeadAttention, Attention, PackedAttention,
PackedMultiHeadAttention) to support broadcast attention bias on CUDA
and CPU EPs.
- [x] Update ROCm, DML and WebGPU naming to be consistent. (Note that
those EPs do not support broadcasting attention_bias for now).
- [x] Add attention bias tests for MultiHeadAttention.
- [x] Update operator documents
- [x] Update benchmark script
Other changes:
* Fix some checks in multihead-attention.ts
* Add helper functions to dump tensors given dimensions.
### Description
See
454996d496
for manual changes (excluded auto-generated formatting changes)
### Why
Because the toolsets for old clang-format is out-of-date. This reduces
the development efficiency.
- The NPM package `clang-format` is already in maintenance mode. not
updated since 2 years ago.
- The VSCode extension for clang-format is not maintained for a while,
and a recent Node.js security update made it not working at all in
Windows.
No one in community seems interested in fixing those.
Choose Prettier as it is the most popular TS/JS formatter.
### How to merge
It's easy to break the build:
- Be careful of any new commits on main not included in this PR.
- Be careful that after this PR is merged, other PRs that already passed
CI can merge.
So, make sure there is no new commits before merging this one, and
invalidate js PRs that already passed CI, force them to merge to latest.
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.
### Description
Added DequantizeLinear operator for JSEP.
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
### Description
This PR adds a new option `ort.env.wasm.wasmBinary`, which allows user
to set to a buffer containing preload .wasm file content.
This PR should resolve the problem from latest discussion in #20876.
Bug:https://github.com/microsoft/onnxruntime/issues/21467
### Description
<!-- Describe your changes. -->
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
### Description
<!-- Describe your changes. -->
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
This var has been initialized to 0 in tint, so no need extra loop to do
it again:
```
float tint_symbol_52[1][4] = (float[1][4])0;
{
for(int tint_symbol_53 = 0; (tint_symbol_53 < 1); tint_symbol_53 = (tint_symbol_53 + 1)) {
{
for(int tint_symbol_54 = 0; (tint_symbol_54 < 4); tint_symbol_54 = (tint_symbol_54 + 1)) {
tint_symbol_52[min(uint(tint_symbol_53), 0u)][min(uint(tint_symbol_54), 3u)] = 0.0f;
}
}
}
}
```
### Description
<!-- Describe your changes. -->
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
### Description
There are so many typos reported by the review dog, [Optional Lint]
actions (example:
https://github.com/microsoft/onnxruntime/actions/runs/9864564489/job/27239732367),
this PR is to fix some of them.
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
---------
Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
### Description
This PR enables the API added in #20816 as well as moving context
creation to JS.
### Motivation and Context
In order to enable I/O Binding with the upcoming
[MLBuffer](https://github.com/webmachinelearning/webnn/issues/542) API
in the WebNN specification, we need to share the same `MLContext` across
multiple sessions. This is because `MLBuffer`s are restricted to the
`MLContext` where they were created. This PR enables developers to use
the same `MLContext` across multiple sessions.
### Description
<!-- Describe your changes. -->
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
### Description
skip default `locateFile()` when dynamic import is disabled. This allows
the file to work with bundlers to load WebAssembly file correctly if
`env.wasm.wasmPaths` is not set.
### Description
<!-- Describe your changes. -->
This PR allows to build ORT web to `ort{.all|.webgpu}.bundle.min.mjs`,
which does not have any dynamic import. This makes it possible to use
ort web via static import in service worker.
Fixes#20876
### Description
<!-- Describe your changes. -->
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
