[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270) - #21869

Open
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom
RanjithRagavan:feature/add-op-bucketize
Open

[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270)#21869
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom
RanjithRagavan:feature/add-op-bucketize

Conversation

@RanjithRagavan

@RanjithRagavanRanjithRagavan commented Aug 15, 2026•
edited
Loading

Copy link
Copy Markdown
Contributor

Summary

Fixes#20270

This PR adds portable CPU kernel implementations for aten::bucketize.Tensor_out and aten::bucketize.Scalar_out.

torch.bucketize is used by model architectures that ExecuTorch targets but currently cannot run on the portable CPU backend:

  • Vision-language multimodal models (e.g., Llama 3.2 Vision) — coordinate bucketing for positional encoding discretization in examples/qualcomm/oss_scripts/llama/model/vision_encoder.py (torch.bucketize(frac_h, boundaries, right=True)).
  • KV-cache compression (TurboQuant 4-bit) — non-uniform vector quantization bin lookup in extension/llm/modules/turboquant/kv_cache.py (torch.bucketize(rotated, self.boundaries)).
  • On-device tabular / recommendation models — continuous feature discretization (the original report in kernel 'aten::bucketize.Tensor_out' not found. #20270 came from an Android deployment).

Without these kernels, exported models containing torch.bucketize fail at load time with kernel 'aten::bucketize.Tensor_out' not found (see #20270 for a minimal repro).

Implementation details

  • Binary search over sorted boundaries: std::upper_bound for right=False, std::lower_bound for right=True. Complexity is O(N log M), where N is the number of input elements and M the number of boundaries.
  • Output dtype is controlled by out_int32: ScalarType::Int (int32) when true, ScalarType::Long (int64) otherwise, validated against the out tensor.
  • All real dtypes plus Half/BFloat16 are supported for both input and boundaries via ET_SWITCH_REALHBF16_TYPES. Mixed-dtype inputs (e.g., integer input with floating-point boundaries) are compared after promotion to double, matching ATen's type-promotion behavior.
  • Edge-case semantics match the ATen CPU kernel: NaN inputs map to index boundaries.numel(), empty boundaries produce all zeros, empty inputs are a no-op, and the Scalar overload produces a 0-dim output tensor.

Registration

  • kernels/portable/functions.yaml: bucketize.Tensor_out and bucketize.Scalar_out
  • shim_et/xplat/executorch/kernels/portable/op_registration_util.bzl: op_bucketize target
  • Test wiring in kernels/test/CMakeLists.txt and kernels/test/targets.bzl

Test plan

New GoogleTest suite kernels/test/op_bucketize_test.cpp, registered for both aten and portable modes so the portable kernel is validated directly against the ATen reference implementation. Coverage:

  • right=True / right=False bucket-boundary semantics on 1-D and multi-dimensional inputs
  • Both output dtypes (int32 via out_int32=True, int64 default)
  • Mixed input/boundary dtypes (int input, float boundaries)
  • NaN handling for both right modes
  • Empty input tensor and empty boundaries
  • Scalar overload with float and integer scalars, both output dtypes

Test command:

ctest -R op_bucketize_test

@RanjithRagavan
Add portable CPU kernel for aten::bucketize (fixespytorch#20270)
a022e1a
- Implemented portable kernels for bucketize.Tensor_out and bucketize.Scalar_out in kernels/portable/cpu/op_bucketize.cpp.
- Supported both 32-bit (int32) and 64-bit (int64) output tensor dtypes via out_int32 argument.
- Implemented binary search using std::upper_bound (right=False) and std::lower_bound (right=True) with logarithmic complexity O(N log M).
- Added multi-dtype support across floating-point (Float, Double, Half, BFloat16) and integral dtypes, including cross-dtype comparisons and IEEE-754 NaN handling.
- Registered operators in functions.yaml, CMakeLists.txt, targets.bzl, and op_registration_util.bzl.
- Added comprehensive GTest unit test suite in kernels/test/op_bucketize_test.cpp covering 1D/2D/3D tensors, scalar inputs, empty inputs/boundaries, right flags, and NaN handling.
@pytorch-bot

pytorch-botBot commented Aug 15, 2026•
edited
Loading

Copy link
Copy Markdown

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21869

Note: Links to docs will display an error until the docs builds have been completed.

⚠️ 21 Awaiting Approval

As of commit f62f1ce with merge base 9bf7e25 (image):

AWAITING APPROVAL - The following workflows need approval before CI can run:

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@meta-clameta-claBot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Aug 15, 2026
@RanjithRagavan

RanjithRagavan commented Aug 15, 2026

Copy link
Copy Markdown
ContributorAuthor

@pytorchbot label "release notes: ops & kernels"

@RanjithRagavan

RanjithRagavan commented Aug 15, 2026

Copy link
Copy Markdown
ContributorAuthor

@pytorchbot label "module: kernels"

@pytorch-botpytorch-botBot added release notes: ops & kernels Changes to the opset and any new / changed kernel implementations module: kernels Issues related to kernel libraries and utilities, and code under kernels/ labels Aug 15, 2026
@GallinatorGallinator mentioned this pull request Aug 16, 2026
Open
@RanjithRagavan

RanjithRagavan commented Aug 19, 2026

Copy link
Copy Markdown
ContributorAuthor

@claude review this PR and suggest if any change to address

@RanjithRagavan

RanjithRagavan commented Aug 26, 2026•
edited
Loading

Copy link
Copy Markdown
ContributorAuthor

@Gasoonjia can you please review and add your feedback

Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@larryliu0820larryliu0820Awaiting requested review from larryliu0820larryliu0820 is a code owner
@kirklandsignkirklandsignAwaiting requested review from kirklandsignkirklandsign is a code owner
@manuelcandalesmanuelcandalesAwaiting requested review from manuelcandalesmanuelcandales is a code owner
@GasoonjiaGasoonjiaAwaiting requested review from Gasoonjia

At least 1 approving review is required to merge this pull request.

Assignees

No one assigned

Labels

CLA SignedThis label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.module: kernelsIssues related to kernel libraries and utilities, and code under kernels/release notes: ops & kernelsChanges to the opset and any new / changed kernel implementations

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

kernel 'aten::bucketize.Tensor_out' not found.

2 participants

@RanjithRagavan@nil-is-all
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270) - #21869
Open
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Open
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270)#21869
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Conversation
@RanjithRagavan
@RanjithRagavanRanjithRagavan
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

Contributor
Summary
Fixes#20270
This PR adds portable CPU kernel implementations for aten::bucketize.Tensor_out and aten::bucketize.Scalar_out.
torch.bucketize is used by model architectures that ExecuTorch targets but currently cannot run on the portable CPU backend:
  • Vision-language multimodal models (e.g., Llama 3.2 Vision) — coordinate bucketing for positional encoding discretization in examples/qualcomm/oss_scripts/llama/model/vision_encoder.py (torch.bucketize(frac_h, boundaries, right=True)).
  • KV-cache compression (TurboQuant 4-bit) — non-uniform vector quantization bin lookup in extension/llm/modules/turboquant/kv_cache.py (torch.bucketize(rotated, self.boundaries)).
  • On-device tabular / recommendation models — continuous feature discretization (the original report in kernel 'aten::bucketize.Tensor_out' not found. #20270 came from an Android deployment).
Without these kernels, exported models containing torch.bucketize fail at load time with kernel 'aten::bucketize.Tensor_out' not found (see #20270 for a minimal repro).
Implementation details
  • Binary search over sorted boundaries: std::upper_bound for right=False, std::lower_bound for right=True. Complexity is O(N log M), where N is the number of input elements and M the number of boundaries.
  • Output dtype is controlled by out_int32: ScalarType::Int (int32) when true, ScalarType::Long (int64) otherwise, validated against the out tensor.
  • All real dtypes plus Half/BFloat16 are supported for both input and boundaries via ET_SWITCH_REALHBF16_TYPES. Mixed-dtype inputs (e.g., integer input with floating-point boundaries) are compared after promotion to double, matching ATen's type-promotion behavior.
  • Edge-case semantics match the ATen CPU kernel: NaN inputs map to index boundaries.numel(), empty boundaries produce all zeros, empty inputs are a no-op, and the Scalar overload produces a 0-dim output tensor.
Registration
  • kernels/portable/functions.yaml: bucketize.Tensor_out and bucketize.Scalar_out
  • shim_et/xplat/executorch/kernels/portable/op_registration_util.bzl: op_bucketize target
  • Test wiring in kernels/test/CMakeLists.txt and kernels/test/targets.bzl
Test plan
New GoogleTest suite kernels/test/op_bucketize_test.cpp, registered for both aten and portable modes so the portable kernel is validated directly against the ATen reference implementation. Coverage:
  • right=True / right=False bucket-boundary semantics on 1-D and multi-dimensional inputs
  • Both output dtypes (int32 via out_int32=True, int64 default)
  • Mixed input/boundary dtypes (int input, float boundaries)
  • NaN handling for both right modes
  • Empty input tensor and empty boundaries
  • Scalar overload with float and integer scalars, both output dtypes
Test command:
ctest -R op_bucketize_test

@RanjithRagavan
Add portable CPU kernel for aten::bucketize (fixespytorch#20270)
a022e1a
- Implemented portable kernels for bucketize.Tensor_out and bucketize.Scalar_out in kernels/portable/cpu/op_bucketize.cpp.
- Supported both 32-bit (int32) and 64-bit (int64) output tensor dtypes via out_int32 argument.
- Implemented binary search using std::upper_bound (right=False) and std::lower_bound (right=True) with logarithmic complexity O(N log M).
- Added multi-dtype support across floating-point (Float, Double, Half, BFloat16) and integral dtypes, including cross-dtype comparisons and IEEE-754 NaN handling.
- Registered operators in functions.yaml, CMakeLists.txt, targets.bzl, and op_registration_util.bzl.
- Added comprehensive GTest unit test suite in kernels/test/op_bucketize_test.cpp covering 1D/2D/3D tensors, scalar inputs, empty inputs/boundaries, right flags, and NaN handling.
@pytorch-bot
pytorch-botBot
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

🔗 Helpful Links
🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21869
Note: Links to docs will display an error until the docs builds have been completed.
⚠️ 21 Awaiting Approval
As of commit f62f1ce with merge base 9bf7e25 (image):
AWAITING APPROVAL - The following workflows need approval before CI can run:
This comment was automatically generated by Dr. CI and updates every 15 minutes.
@meta-clameta-claBot
added
the 
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
label
Aug 15, 2026
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "release notes: ops & kernels"
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "module: kernels"
@pytorch-botpytorch-botBot
added

release notes: ops & kernels
Changes to the opset and any new / changed kernel implementations
module: kernels
Issues related to kernel libraries and utilities, and code under kernels/
labels
Aug 15, 2026
@GallinatorGallinator
mentioned this pull request
Aug 16, 2026
 Open

@RanjithRagavan
RanjithRagavan
commented
Aug 19, 2026

Copy link


Copy Markdown

ContributorAuthor
@claude review this PR and suggest if any change to address
@RanjithRagavan
RanjithRagavan
commented
Aug 26, 2026•

edited

Loading

Copy link


Copy Markdown

ContributorAuthor
@Gasoonjia can you please review and add your feedback
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers

@larryliu0820larryliu0820Awaiting requested review from larryliu0820larryliu0820 is a code owner
@kirklandsignkirklandsignAwaiting requested review from kirklandsignkirklandsign is a code owner
@manuelcandalesmanuelcandalesAwaiting requested review from manuelcandalesmanuelcandales is a code owner
@GasoonjiaGasoonjiaAwaiting requested review from Gasoonjia

At least 1 approving review is required to merge this pull request.


Assignees


No one assigned


Labels

CLA SignedThis label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.module: kernelsIssues related to kernel libraries and utilities, and code under kernels/release notes: ops & kernelsChanges to the opset and any new / changed kernel implementations

Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

kernel 'aten::bucketize.Tensor_out' not found.


2 participants

@RanjithRagavan@nil-is-all

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270) - #21869
Open
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Open
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270)#21869
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Conversation
@RanjithRagavan
@RanjithRagavanRanjithRagavan
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

Contributor
Summary
Fixes#20270
This PR adds portable CPU kernel implementations for aten::bucketize.Tensor_out and aten::bucketize.Scalar_out.
torch.bucketize is used by model architectures that ExecuTorch targets but currently cannot run on the portable CPU backend:
  • Vision-language multimodal models (e.g., Llama 3.2 Vision) — coordinate bucketing for positional encoding discretization in examples/qualcomm/oss_scripts/llama/model/vision_encoder.py (torch.bucketize(frac_h, boundaries, right=True)).
  • KV-cache compression (TurboQuant 4-bit) — non-uniform vector quantization bin lookup in extension/llm/modules/turboquant/kv_cache.py (torch.bucketize(rotated, self.boundaries)).
  • On-device tabular / recommendation models — continuous feature discretization (the original report in kernel 'aten::bucketize.Tensor_out' not found. #20270 came from an Android deployment).
Without these kernels, exported models containing torch.bucketize fail at load time with kernel 'aten::bucketize.Tensor_out' not found (see #20270 for a minimal repro).
Implementation details
  • Binary search over sorted boundaries: std::upper_bound for right=False, std::lower_bound for right=True. Complexity is O(N log M), where N is the number of input elements and M the number of boundaries.
  • Output dtype is controlled by out_int32: ScalarType::Int (int32) when true, ScalarType::Long (int64) otherwise, validated against the out tensor.
  • All real dtypes plus Half/BFloat16 are supported for both input and boundaries via ET_SWITCH_REALHBF16_TYPES. Mixed-dtype inputs (e.g., integer input with floating-point boundaries) are compared after promotion to double, matching ATen's type-promotion behavior.
  • Edge-case semantics match the ATen CPU kernel: NaN inputs map to index boundaries.numel(), empty boundaries produce all zeros, empty inputs are a no-op, and the Scalar overload produces a 0-dim output tensor.
Registration
  • kernels/portable/functions.yaml: bucketize.Tensor_out and bucketize.Scalar_out
  • shim_et/xplat/executorch/kernels/portable/op_registration_util.bzl: op_bucketize target
  • Test wiring in kernels/test/CMakeLists.txt and kernels/test/targets.bzl
Test plan
New GoogleTest suite kernels/test/op_bucketize_test.cpp, registered for both aten and portable modes so the portable kernel is validated directly against the ATen reference implementation. Coverage:
  • right=True / right=False bucket-boundary semantics on 1-D and multi-dimensional inputs
  • Both output dtypes (int32 via out_int32=True, int64 default)
  • Mixed input/boundary dtypes (int input, float boundaries)
  • NaN handling for both right modes
  • Empty input tensor and empty boundaries
  • Scalar overload with float and integer scalars, both output dtypes
Test command:
ctest -R op_bucketize_test

@RanjithRagavan
Add portable CPU kernel for aten::bucketize (fixespytorch#20270)
a022e1a
- Implemented portable kernels for bucketize.Tensor_out and bucketize.Scalar_out in kernels/portable/cpu/op_bucketize.cpp.
- Supported both 32-bit (int32) and 64-bit (int64) output tensor dtypes via out_int32 argument.
- Implemented binary search using std::upper_bound (right=False) and std::lower_bound (right=True) with logarithmic complexity O(N log M).
- Added multi-dtype support across floating-point (Float, Double, Half, BFloat16) and integral dtypes, including cross-dtype comparisons and IEEE-754 NaN handling.
- Registered operators in functions.yaml, CMakeLists.txt, targets.bzl, and op_registration_util.bzl.
- Added comprehensive GTest unit test suite in kernels/test/op_bucketize_test.cpp covering 1D/2D/3D tensors, scalar inputs, empty inputs/boundaries, right flags, and NaN handling.
@pytorch-bot
pytorch-botBot
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

🔗 Helpful Links
🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21869
Note: Links to docs will display an error until the docs builds have been completed.
⚠️ 21 Awaiting Approval
As of commit f62f1ce with merge base 9bf7e25 (image):
AWAITING APPROVAL - The following workflows need approval before CI can run:
This comment was automatically generated by Dr. CI and updates every 15 minutes.
@meta-clameta-claBot
added
the 
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
label
Aug 15, 2026
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "release notes: ops & kernels"
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "module: kernels"
@pytorch-botpytorch-botBot
added

release notes: ops & kernels
Changes to the opset and any new / changed kernel implementations
module: kernels
Issues related to kernel libraries and utilities, and code under kernels/
labels
Aug 15, 2026
@GallinatorGallinator
mentioned this pull request
Aug 16, 2026
 Open

@RanjithRagavan
RanjithRagavan
commented
Aug 19, 2026

Copy link


Copy Markdown

ContributorAuthor
@claude review this PR and suggest if any change to address
@RanjithRagavan
RanjithRagavan
commented
Aug 26, 2026•

edited

Loading

Copy link


Copy Markdown

ContributorAuthor
@Gasoonjia can you please review and add your feedback
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers

@larryliu0820larryliu0820Awaiting requested review from larryliu0820larryliu0820 is a code owner
@kirklandsignkirklandsignAwaiting requested review from kirklandsignkirklandsign is a code owner
@manuelcandalesmanuelcandalesAwaiting requested review from manuelcandalesmanuelcandales is a code owner
@GasoonjiaGasoonjiaAwaiting requested review from Gasoonjia

At least 1 approving review is required to merge this pull request.


Assignees


No one assigned


Labels

CLA SignedThis label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.module: kernelsIssues related to kernel libraries and utilities, and code under kernels/release notes: ops & kernelsChanges to the opset and any new / changed kernel implementations

Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

kernel 'aten::bucketize.Tensor_out' not found.


2 participants

@RanjithRagavan@nil-is-all

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270) - #21869
Open
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Open
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270)#21869
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Conversation
@RanjithRagavan
@RanjithRagavanRanjithRagavan
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

Contributor
Summary
Fixes#20270
This PR adds portable CPU kernel implementations for aten::bucketize.Tensor_out and aten::bucketize.Scalar_out.
torch.bucketize is used by model architectures that ExecuTorch targets but currently cannot run on the portable CPU backend:
  • Vision-language multimodal models (e.g., Llama 3.2 Vision) — coordinate bucketing for positional encoding discretization in examples/qualcomm/oss_scripts/llama/model/vision_encoder.py (torch.bucketize(frac_h, boundaries, right=True)).
  • KV-cache compression (TurboQuant 4-bit) — non-uniform vector quantization bin lookup in extension/llm/modules/turboquant/kv_cache.py (torch.bucketize(rotated, self.boundaries)).
  • On-device tabular / recommendation models — continuous feature discretization (the original report in kernel 'aten::bucketize.Tensor_out' not found. #20270 came from an Android deployment).
Without these kernels, exported models containing torch.bucketize fail at load time with kernel 'aten::bucketize.Tensor_out' not found (see #20270 for a minimal repro).
Implementation details
  • Binary search over sorted boundaries: std::upper_bound for right=False, std::lower_bound for right=True. Complexity is O(N log M), where N is the number of input elements and M the number of boundaries.
  • Output dtype is controlled by out_int32: ScalarType::Int (int32) when true, ScalarType::Long (int64) otherwise, validated against the out tensor.
  • All real dtypes plus Half/BFloat16 are supported for both input and boundaries via ET_SWITCH_REALHBF16_TYPES. Mixed-dtype inputs (e.g., integer input with floating-point boundaries) are compared after promotion to double, matching ATen's type-promotion behavior.
  • Edge-case semantics match the ATen CPU kernel: NaN inputs map to index boundaries.numel(), empty boundaries produce all zeros, empty inputs are a no-op, and the Scalar overload produces a 0-dim output tensor.
Registration
  • kernels/portable/functions.yaml: bucketize.Tensor_out and bucketize.Scalar_out
  • shim_et/xplat/executorch/kernels/portable/op_registration_util.bzl: op_bucketize target
  • Test wiring in kernels/test/CMakeLists.txt and kernels/test/targets.bzl
Test plan
New GoogleTest suite kernels/test/op_bucketize_test.cpp, registered for both aten and portable modes so the portable kernel is validated directly against the ATen reference implementation. Coverage:
  • right=True / right=False bucket-boundary semantics on 1-D and multi-dimensional inputs
  • Both output dtypes (int32 via out_int32=True, int64 default)
  • Mixed input/boundary dtypes (int input, float boundaries)
  • NaN handling for both right modes
  • Empty input tensor and empty boundaries
  • Scalar overload with float and integer scalars, both output dtypes
Test command:
ctest -R op_bucketize_test

@RanjithRagavan
Add portable CPU kernel for aten::bucketize (fixespytorch#20270)
a022e1a
- Implemented portable kernels for bucketize.Tensor_out and bucketize.Scalar_out in kernels/portable/cpu/op_bucketize.cpp.
- Supported both 32-bit (int32) and 64-bit (int64) output tensor dtypes via out_int32 argument.
- Implemented binary search using std::upper_bound (right=False) and std::lower_bound (right=True) with logarithmic complexity O(N log M).
- Added multi-dtype support across floating-point (Float, Double, Half, BFloat16) and integral dtypes, including cross-dtype comparisons and IEEE-754 NaN handling.
- Registered operators in functions.yaml, CMakeLists.txt, targets.bzl, and op_registration_util.bzl.
- Added comprehensive GTest unit test suite in kernels/test/op_bucketize_test.cpp covering 1D/2D/3D tensors, scalar inputs, empty inputs/boundaries, right flags, and NaN handling.
@pytorch-bot
pytorch-botBot
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

🔗 Helpful Links
🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21869
Note: Links to docs will display an error until the docs builds have been completed.
⚠️ 21 Awaiting Approval
As of commit f62f1ce with merge base 9bf7e25 (image):
AWAITING APPROVAL - The following workflows need approval before CI can run:
This comment was automatically generated by Dr. CI and updates every 15 minutes.
@meta-clameta-claBot
added
the 
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
label
Aug 15, 2026
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "release notes: ops & kernels"
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "module: kernels"
@pytorch-botpytorch-botBot
added

release notes: ops & kernels
Changes to the opset and any new / changed kernel implementations
module: kernels
Issues related to kernel libraries and utilities, and code under kernels/
labels
Aug 15, 2026
@GallinatorGallinator
mentioned this pull request
Aug 16, 2026
 Open

@RanjithRagavan
RanjithRagavan
commented
Aug 19, 2026

Copy link


Copy Markdown

ContributorAuthor
@claude review this PR and suggest if any change to address
@RanjithRagavan
RanjithRagavan
commented
Aug 26, 2026•

edited

Loading

Copy link


Copy Markdown

ContributorAuthor
@Gasoonjia can you please review and add your feedback
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers

@larryliu0820larryliu0820Awaiting requested review from larryliu0820larryliu0820 is a code owner
@kirklandsignkirklandsignAwaiting requested review from kirklandsignkirklandsign is a code owner
@manuelcandalesmanuelcandalesAwaiting requested review from manuelcandalesmanuelcandales is a code owner
@GasoonjiaGasoonjiaAwaiting requested review from Gasoonjia

At least 1 approving review is required to merge this pull request.


Assignees


No one assigned


Labels

CLA SignedThis label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.module: kernelsIssues related to kernel libraries and utilities, and code under kernels/release notes: ops & kernelsChanges to the opset and any new / changed kernel implementations

Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

kernel 'aten::bucketize.Tensor_out' not found.


2 participants

@RanjithRagavan@nil-is-all

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270) - #21869
Open
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Open
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270)#21869
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Conversation
@RanjithRagavan
@RanjithRagavanRanjithRagavan
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

Contributor
Summary
Fixes#20270
This PR adds portable CPU kernel implementations for aten::bucketize.Tensor_out and aten::bucketize.Scalar_out.
torch.bucketize is used by model architectures that ExecuTorch targets but currently cannot run on the portable CPU backend:
  • Vision-language multimodal models (e.g., Llama 3.2 Vision) — coordinate bucketing for positional encoding discretization in examples/qualcomm/oss_scripts/llama/model/vision_encoder.py (torch.bucketize(frac_h, boundaries, right=True)).
  • KV-cache compression (TurboQuant 4-bit) — non-uniform vector quantization bin lookup in extension/llm/modules/turboquant/kv_cache.py (torch.bucketize(rotated, self.boundaries)).
  • On-device tabular / recommendation models — continuous feature discretization (the original report in kernel 'aten::bucketize.Tensor_out' not found. #20270 came from an Android deployment).
Without these kernels, exported models containing torch.bucketize fail at load time with kernel 'aten::bucketize.Tensor_out' not found (see #20270 for a minimal repro).
Implementation details
  • Binary search over sorted boundaries: std::upper_bound for right=False, std::lower_bound for right=True. Complexity is O(N log M), where N is the number of input elements and M the number of boundaries.
  • Output dtype is controlled by out_int32: ScalarType::Int (int32) when true, ScalarType::Long (int64) otherwise, validated against the out tensor.
  • All real dtypes plus Half/BFloat16 are supported for both input and boundaries via ET_SWITCH_REALHBF16_TYPES. Mixed-dtype inputs (e.g., integer input with floating-point boundaries) are compared after promotion to double, matching ATen's type-promotion behavior.
  • Edge-case semantics match the ATen CPU kernel: NaN inputs map to index boundaries.numel(), empty boundaries produce all zeros, empty inputs are a no-op, and the Scalar overload produces a 0-dim output tensor.
Registration
  • kernels/portable/functions.yaml: bucketize.Tensor_out and bucketize.Scalar_out
  • shim_et/xplat/executorch/kernels/portable/op_registration_util.bzl: op_bucketize target
  • Test wiring in kernels/test/CMakeLists.txt and kernels/test/targets.bzl
Test plan
New GoogleTest suite kernels/test/op_bucketize_test.cpp, registered for both aten and portable modes so the portable kernel is validated directly against the ATen reference implementation. Coverage:
  • right=True / right=False bucket-boundary semantics on 1-D and multi-dimensional inputs
  • Both output dtypes (int32 via out_int32=True, int64 default)
  • Mixed input/boundary dtypes (int input, float boundaries)
  • NaN handling for both right modes
  • Empty input tensor and empty boundaries
  • Scalar overload with float and integer scalars, both output dtypes
Test command:
ctest -R op_bucketize_test

@RanjithRagavan
Add portable CPU kernel for aten::bucketize (fixespytorch#20270)
a022e1a
- Implemented portable kernels for bucketize.Tensor_out and bucketize.Scalar_out in kernels/portable/cpu/op_bucketize.cpp.
- Supported both 32-bit (int32) and 64-bit (int64) output tensor dtypes via out_int32 argument.
- Implemented binary search using std::upper_bound (right=False) and std::lower_bound (right=True) with logarithmic complexity O(N log M).
- Added multi-dtype support across floating-point (Float, Double, Half, BFloat16) and integral dtypes, including cross-dtype comparisons and IEEE-754 NaN handling.
- Registered operators in functions.yaml, CMakeLists.txt, targets.bzl, and op_registration_util.bzl.
- Added comprehensive GTest unit test suite in kernels/test/op_bucketize_test.cpp covering 1D/2D/3D tensors, scalar inputs, empty inputs/boundaries, right flags, and NaN handling.
@pytorch-bot
pytorch-botBot
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

🔗 Helpful Links
🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21869
Note: Links to docs will display an error until the docs builds have been completed.
⚠️ 21 Awaiting Approval
As of commit f62f1ce with merge base 9bf7e25 (image):
AWAITING APPROVAL - The following workflows need approval before CI can run:
This comment was automatically generated by Dr. CI and updates every 15 minutes.
@meta-clameta-claBot
added
the 
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
label
Aug 15, 2026
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "release notes: ops & kernels"
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "module: kernels"
@pytorch-botpytorch-botBot
added

release notes: ops & kernels
Changes to the opset and any new / changed kernel implementations
module: kernels
Issues related to kernel libraries and utilities, and code under kernels/
labels
Aug 15, 2026
@GallinatorGallinator
mentioned this pull request
Aug 16, 2026
 Open

@RanjithRagavan
RanjithRagavan
commented
Aug 19, 2026

Copy link


Copy Markdown

ContributorAuthor
@claude review this PR and suggest if any change to address
@RanjithRagavan
RanjithRagavan
commented
Aug 26, 2026•

edited

Loading

Copy link


Copy Markdown

ContributorAuthor
@Gasoonjia can you please review and add your feedback
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers

@larryliu0820larryliu0820Awaiting requested review from larryliu0820larryliu0820 is a code owner
@kirklandsignkirklandsignAwaiting requested review from kirklandsignkirklandsign is a code owner
@manuelcandalesmanuelcandalesAwaiting requested review from manuelcandalesmanuelcandales is a code owner
@GasoonjiaGasoonjiaAwaiting requested review from Gasoonjia

At least 1 approving review is required to merge this pull request.


Assignees


No one assigned


Labels

CLA SignedThis label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.module: kernelsIssues related to kernel libraries and utilities, and code under kernels/release notes: ops & kernelsChanges to the opset and any new / changed kernel implementations

Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

kernel 'aten::bucketize.Tensor_out' not found.


2 participants

@RanjithRagavan@nil-is-all

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270) - #21869
Open
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Open
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270)#21869
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Conversation
@RanjithRagavan
@RanjithRagavanRanjithRagavan
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

Contributor
Summary
Fixes#20270
This PR adds portable CPU kernel implementations for aten::bucketize.Tensor_out and aten::bucketize.Scalar_out.
torch.bucketize is used by model architectures that ExecuTorch targets but currently cannot run on the portable CPU backend:
  • Vision-language multimodal models (e.g., Llama 3.2 Vision) — coordinate bucketing for positional encoding discretization in examples/qualcomm/oss_scripts/llama/model/vision_encoder.py (torch.bucketize(frac_h, boundaries, right=True)).
  • KV-cache compression (TurboQuant 4-bit) — non-uniform vector quantization bin lookup in extension/llm/modules/turboquant/kv_cache.py (torch.bucketize(rotated, self.boundaries)).
  • On-device tabular / recommendation models — continuous feature discretization (the original report in kernel 'aten::bucketize.Tensor_out' not found. #20270 came from an Android deployment).
Without these kernels, exported models containing torch.bucketize fail at load time with kernel 'aten::bucketize.Tensor_out' not found (see #20270 for a minimal repro).
Implementation details
  • Binary search over sorted boundaries: std::upper_bound for right=False, std::lower_bound for right=True. Complexity is O(N log M), where N is the number of input elements and M the number of boundaries.
  • Output dtype is controlled by out_int32: ScalarType::Int (int32) when true, ScalarType::Long (int64) otherwise, validated against the out tensor.
  • All real dtypes plus Half/BFloat16 are supported for both input and boundaries via ET_SWITCH_REALHBF16_TYPES. Mixed-dtype inputs (e.g., integer input with floating-point boundaries) are compared after promotion to double, matching ATen's type-promotion behavior.
  • Edge-case semantics match the ATen CPU kernel: NaN inputs map to index boundaries.numel(), empty boundaries produce all zeros, empty inputs are a no-op, and the Scalar overload produces a 0-dim output tensor.
Registration
  • kernels/portable/functions.yaml: bucketize.Tensor_out and bucketize.Scalar_out
  • shim_et/xplat/executorch/kernels/portable/op_registration_util.bzl: op_bucketize target
  • Test wiring in kernels/test/CMakeLists.txt and kernels/test/targets.bzl
Test plan
New GoogleTest suite kernels/test/op_bucketize_test.cpp, registered for both aten and portable modes so the portable kernel is validated directly against the ATen reference implementation. Coverage:
  • right=True / right=False bucket-boundary semantics on 1-D and multi-dimensional inputs
  • Both output dtypes (int32 via out_int32=True, int64 default)
  • Mixed input/boundary dtypes (int input, float boundaries)
  • NaN handling for both right modes
  • Empty input tensor and empty boundaries
  • Scalar overload with float and integer scalars, both output dtypes
Test command:
ctest -R op_bucketize_test

@RanjithRagavan
Add portable CPU kernel for aten::bucketize (fixespytorch#20270)
a022e1a
- Implemented portable kernels for bucketize.Tensor_out and bucketize.Scalar_out in kernels/portable/cpu/op_bucketize.cpp.
- Supported both 32-bit (int32) and 64-bit (int64) output tensor dtypes via out_int32 argument.
- Implemented binary search using std::upper_bound (right=False) and std::lower_bound (right=True) with logarithmic complexity O(N log M).
- Added multi-dtype support across floating-point (Float, Double, Half, BFloat16) and integral dtypes, including cross-dtype comparisons and IEEE-754 NaN handling.
- Registered operators in functions.yaml, CMakeLists.txt, targets.bzl, and op_registration_util.bzl.
- Added comprehensive GTest unit test suite in kernels/test/op_bucketize_test.cpp covering 1D/2D/3D tensors, scalar inputs, empty inputs/boundaries, right flags, and NaN handling.
@pytorch-bot
pytorch-botBot
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

🔗 Helpful Links
🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21869
Note: Links to docs will display an error until the docs builds have been completed.
⚠️ 21 Awaiting Approval
As of commit f62f1ce with merge base 9bf7e25 (image):
AWAITING APPROVAL - The following workflows need approval before CI can run:
This comment was automatically generated by Dr. CI and updates every 15 minutes.
@meta-clameta-claBot
added
the 
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
label
Aug 15, 2026
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "release notes: ops & kernels"
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "module: kernels"
@pytorch-botpytorch-botBot
added

release notes: ops & kernels
Changes to the opset and any new / changed kernel implementations
module: kernels
Issues related to kernel libraries and utilities, and code under kernels/
labels
Aug 15, 2026
@GallinatorGallinator
mentioned this pull request
Aug 16, 2026
 Open

@RanjithRagavan
RanjithRagavan
commented
Aug 19, 2026

Copy link


Copy Markdown

ContributorAuthor
@claude review this PR and suggest if any change to address
@RanjithRagavan
RanjithRagavan
commented
Aug 26, 2026•

edited

Loading

Copy link


Copy Markdown

ContributorAuthor
@Gasoonjia can you please review and add your feedback
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers

@larryliu0820larryliu0820Awaiting requested review from larryliu0820larryliu0820 is a code owner
@kirklandsignkirklandsignAwaiting requested review from kirklandsignkirklandsign is a code owner
@manuelcandalesmanuelcandalesAwaiting requested review from manuelcandalesmanuelcandales is a code owner
@GasoonjiaGasoonjiaAwaiting requested review from Gasoonjia

At least 1 approving review is required to merge this pull request.


Assignees


No one assigned


Labels

CLA SignedThis label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.module: kernelsIssues related to kernel libraries and utilities, and code under kernels/release notes: ops & kernelsChanges to the opset and any new / changed kernel implementations

Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

kernel 'aten::bucketize.Tensor_out' not found.


2 participants

@RanjithRagavan@nil-is-all

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270) - #21869
Open
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Open
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270)#21869
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Conversation
@RanjithRagavan
@RanjithRagavanRanjithRagavan
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

Contributor
Summary
Fixes#20270
This PR adds portable CPU kernel implementations for aten::bucketize.Tensor_out and aten::bucketize.Scalar_out.
torch.bucketize is used by model architectures that ExecuTorch targets but currently cannot run on the portable CPU backend:
  • Vision-language multimodal models (e.g., Llama 3.2 Vision) — coordinate bucketing for positional encoding discretization in examples/qualcomm/oss_scripts/llama/model/vision_encoder.py (torch.bucketize(frac_h, boundaries, right=True)).
  • KV-cache compression (TurboQuant 4-bit) — non-uniform vector quantization bin lookup in extension/llm/modules/turboquant/kv_cache.py (torch.bucketize(rotated, self.boundaries)).
  • On-device tabular / recommendation models — continuous feature discretization (the original report in kernel 'aten::bucketize.Tensor_out' not found. #20270 came from an Android deployment).
Without these kernels, exported models containing torch.bucketize fail at load time with kernel 'aten::bucketize.Tensor_out' not found (see #20270 for a minimal repro).
Implementation details
  • Binary search over sorted boundaries: std::upper_bound for right=False, std::lower_bound for right=True. Complexity is O(N log M), where N is the number of input elements and M the number of boundaries.
  • Output dtype is controlled by out_int32: ScalarType::Int (int32) when true, ScalarType::Long (int64) otherwise, validated against the out tensor.
  • All real dtypes plus Half/BFloat16 are supported for both input and boundaries via ET_SWITCH_REALHBF16_TYPES. Mixed-dtype inputs (e.g., integer input with floating-point boundaries) are compared after promotion to double, matching ATen's type-promotion behavior.
  • Edge-case semantics match the ATen CPU kernel: NaN inputs map to index boundaries.numel(), empty boundaries produce all zeros, empty inputs are a no-op, and the Scalar overload produces a 0-dim output tensor.
Registration
  • kernels/portable/functions.yaml: bucketize.Tensor_out and bucketize.Scalar_out
  • shim_et/xplat/executorch/kernels/portable/op_registration_util.bzl: op_bucketize target
  • Test wiring in kernels/test/CMakeLists.txt and kernels/test/targets.bzl
Test plan
New GoogleTest suite kernels/test/op_bucketize_test.cpp, registered for both aten and portable modes so the portable kernel is validated directly against the ATen reference implementation. Coverage:
  • right=True / right=False bucket-boundary semantics on 1-D and multi-dimensional inputs
  • Both output dtypes (int32 via out_int32=True, int64 default)
  • Mixed input/boundary dtypes (int input, float boundaries)
  • NaN handling for both right modes
  • Empty input tensor and empty boundaries
  • Scalar overload with float and integer scalars, both output dtypes
Test command:
ctest -R op_bucketize_test

@RanjithRagavan
Add portable CPU kernel for aten::bucketize (fixespytorch#20270)
a022e1a
- Implemented portable kernels for bucketize.Tensor_out and bucketize.Scalar_out in kernels/portable/cpu/op_bucketize.cpp.
- Supported both 32-bit (int32) and 64-bit (int64) output tensor dtypes via out_int32 argument.
- Implemented binary search using std::upper_bound (right=False) and std::lower_bound (right=True) with logarithmic complexity O(N log M).
- Added multi-dtype support across floating-point (Float, Double, Half, BFloat16) and integral dtypes, including cross-dtype comparisons and IEEE-754 NaN handling.
- Registered operators in functions.yaml, CMakeLists.txt, targets.bzl, and op_registration_util.bzl.
- Added comprehensive GTest unit test suite in kernels/test/op_bucketize_test.cpp covering 1D/2D/3D tensors, scalar inputs, empty inputs/boundaries, right flags, and NaN handling.
@pytorch-bot
pytorch-botBot
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

🔗 Helpful Links
🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21869
Note: Links to docs will display an error until the docs builds have been completed.
⚠️ 21 Awaiting Approval
As of commit f62f1ce with merge base 9bf7e25 (image):
AWAITING APPROVAL - The following workflows need approval before CI can run:
This comment was automatically generated by Dr. CI and updates every 15 minutes.
@meta-clameta-claBot
added
the 
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
label
Aug 15, 2026
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "release notes: ops & kernels"
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "module: kernels"
@pytorch-botpytorch-botBot
added

release notes: ops & kernels
Changes to the opset and any new / changed kernel implementations
module: kernels
Issues related to kernel libraries and utilities, and code under kernels/
labels
Aug 15, 2026
@GallinatorGallinator
mentioned this pull request
Aug 16, 2026
 Open

@RanjithRagavan
RanjithRagavan
commented
Aug 19, 2026

Copy link


Copy Markdown

ContributorAuthor
@claude review this PR and suggest if any change to address
@RanjithRagavan
RanjithRagavan
commented
Aug 26, 2026•

edited

Loading

Copy link


Copy Markdown

ContributorAuthor
@Gasoonjia can you please review and add your feedback
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers

@larryliu0820larryliu0820Awaiting requested review from larryliu0820larryliu0820 is a code owner
@kirklandsignkirklandsignAwaiting requested review from kirklandsignkirklandsign is a code owner
@manuelcandalesmanuelcandalesAwaiting requested review from manuelcandalesmanuelcandales is a code owner
@GasoonjiaGasoonjiaAwaiting requested review from Gasoonjia

At least 1 approving review is required to merge this pull request.


Assignees


No one assigned


Labels

CLA SignedThis label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.module: kernelsIssues related to kernel libraries and utilities, and code under kernels/release notes: ops & kernelsChanges to the opset and any new / changed kernel implementations

Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

kernel 'aten::bucketize.Tensor_out' not found.


2 participants

@RanjithRagavan@nil-is-all

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270) - #21869
Open
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Open
[Kernels] Implement portable CPU kernel for aten::bucketize (fixes #20270)#21869
RanjithRagavan wants to merge 7 commits into
pytorch:mainfrom 
RanjithRagavan:feature/add-op-bucketize
Conversation
@RanjithRagavan
@RanjithRagavanRanjithRagavan
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

Contributor
Summary
Fixes#20270
This PR adds portable CPU kernel implementations for aten::bucketize.Tensor_out and aten::bucketize.Scalar_out.
torch.bucketize is used by model architectures that ExecuTorch targets but currently cannot run on the portable CPU backend:
  • Vision-language multimodal models (e.g., Llama 3.2 Vision) — coordinate bucketing for positional encoding discretization in examples/qualcomm/oss_scripts/llama/model/vision_encoder.py (torch.bucketize(frac_h, boundaries, right=True)).
  • KV-cache compression (TurboQuant 4-bit) — non-uniform vector quantization bin lookup in extension/llm/modules/turboquant/kv_cache.py (torch.bucketize(rotated, self.boundaries)).
  • On-device tabular / recommendation models — continuous feature discretization (the original report in kernel 'aten::bucketize.Tensor_out' not found. #20270 came from an Android deployment).
Without these kernels, exported models containing torch.bucketize fail at load time with kernel 'aten::bucketize.Tensor_out' not found (see #20270 for a minimal repro).
Implementation details
  • Binary search over sorted boundaries: std::upper_bound for right=False, std::lower_bound for right=True. Complexity is O(N log M), where N is the number of input elements and M the number of boundaries.
  • Output dtype is controlled by out_int32: ScalarType::Int (int32) when true, ScalarType::Long (int64) otherwise, validated against the out tensor.
  • All real dtypes plus Half/BFloat16 are supported for both input and boundaries via ET_SWITCH_REALHBF16_TYPES. Mixed-dtype inputs (e.g., integer input with floating-point boundaries) are compared after promotion to double, matching ATen's type-promotion behavior.
  • Edge-case semantics match the ATen CPU kernel: NaN inputs map to index boundaries.numel(), empty boundaries produce all zeros, empty inputs are a no-op, and the Scalar overload produces a 0-dim output tensor.
Registration
  • kernels/portable/functions.yaml: bucketize.Tensor_out and bucketize.Scalar_out
  • shim_et/xplat/executorch/kernels/portable/op_registration_util.bzl: op_bucketize target
  • Test wiring in kernels/test/CMakeLists.txt and kernels/test/targets.bzl
Test plan
New GoogleTest suite kernels/test/op_bucketize_test.cpp, registered for both aten and portable modes so the portable kernel is validated directly against the ATen reference implementation. Coverage:
  • right=True / right=False bucket-boundary semantics on 1-D and multi-dimensional inputs
  • Both output dtypes (int32 via out_int32=True, int64 default)
  • Mixed input/boundary dtypes (int input, float boundaries)
  • NaN handling for both right modes
  • Empty input tensor and empty boundaries
  • Scalar overload with float and integer scalars, both output dtypes
Test command:
ctest -R op_bucketize_test

@RanjithRagavan
Add portable CPU kernel for aten::bucketize (fixespytorch#20270)
a022e1a
- Implemented portable kernels for bucketize.Tensor_out and bucketize.Scalar_out in kernels/portable/cpu/op_bucketize.cpp.
- Supported both 32-bit (int32) and 64-bit (int64) output tensor dtypes via out_int32 argument.
- Implemented binary search using std::upper_bound (right=False) and std::lower_bound (right=True) with logarithmic complexity O(N log M).
- Added multi-dtype support across floating-point (Float, Double, Half, BFloat16) and integral dtypes, including cross-dtype comparisons and IEEE-754 NaN handling.
- Registered operators in functions.yaml, CMakeLists.txt, targets.bzl, and op_registration_util.bzl.
- Added comprehensive GTest unit test suite in kernels/test/op_bucketize_test.cpp covering 1D/2D/3D tensors, scalar inputs, empty inputs/boundaries, right flags, and NaN handling.
@pytorch-bot
pytorch-botBot
commented
Aug 15, 2026•

edited

Loading

Copy link


Copy Markdown

🔗 Helpful Links
🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21869
Note: Links to docs will display an error until the docs builds have been completed.
⚠️ 21 Awaiting Approval
As of commit f62f1ce with merge base 9bf7e25 (image):
AWAITING APPROVAL - The following workflows need approval before CI can run:
This comment was automatically generated by Dr. CI and updates every 15 minutes.
@meta-clameta-claBot
added
the 
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
label
Aug 15, 2026
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "release notes: ops & kernels"
@RanjithRagavan
RanjithRagavan
commented
Aug 15, 2026

Copy link


Copy Markdown

ContributorAuthor
@pytorchbot label "module: kernels"
@pytorch-botpytorch-botBot
added

release notes: ops & kernels
Changes to the opset and any new / changed kernel implementations
module: kernels
Issues related to kernel libraries and utilities, and code under kernels/
labels
Aug 15, 2026
@GallinatorGallinator
mentioned this pull request
Aug 16, 2026
 Open

@RanjithRagavan
RanjithRagavan
commented
Aug 19, 2026

Copy link


Copy Markdown

ContributorAuthor
@claude review this PR and suggest if any change to address
@RanjithRagavan
RanjithRagavan
commented
Aug 26, 2026•

edited

Loading

Copy link


Copy Markdown

ContributorAuthor
@Gasoonjia can you please review and add your feedback
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers

@larryliu0820larryliu0820Awaiting requested review from larryliu0820larryliu0820 is a code owner
@kirklandsignkirklandsignAwaiting requested review from kirklandsignkirklandsign is a code owner
@manuelcandalesmanuelcandalesAwaiting requested review from manuelcandalesmanuelcandales is a code owner
@GasoonjiaGasoonjiaAwaiting requested review from Gasoonjia

At least 1 approving review is required to merge this pull request.


Assignees


No one assigned


Labels

CLA SignedThis label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.module: kernelsIssues related to kernel libraries and utilities, and code under kernels/release notes: ops & kernelsChanges to the opset and any new / changed kernel implementations

Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

kernel 'aten::bucketize.Tensor_out' not found.


2 participants

@RanjithRagavan@nil-is-all