add-uint-support

작성자: pytorch

PyTorch 연산자에 부호 없는 정수(uint) 타입 지원을 추가하기 위해 AT_DISPATCH 매크로를 업데이트합니다. uint16, uint32, uint64 타입에 대한 지원을 추가할 때 사용합니다.

npx skills add https://github.com/pytorch/pytorch --skill add-uint-support

Add Unsigned Integer (uint) Support to Operators

This skill helps add support for unsigned integer types (uint16, uint32, uint64) to PyTorch operators by updating their AT_DISPATCH macros.

When to use this skill

Use this skill when:

  • Adding uint16, uint32, or uint64 support to an operator
  • User mentions "unsigned types", "uint support", "barebones unsigned types"
  • Enabling support for kUInt16, kUInt32, kUInt64 in kernels
  • Working with operator implementations that need expanded type coverage

Quick reference

Add unsigned types to existing dispatch:

// Before
AT_DISPATCH_V2(dtype, "op", AT_WRAP([&]() {
  kernel<scalar_t>();
}), AT_EXPAND(AT_ALL_TYPES));

// After (method 1: add unsigned types explicitly)
AT_DISPATCH_V2(dtype, "op", AT_WRAP([&]() {
  kernel<scalar_t>();
}), AT_EXPAND(AT_ALL_TYPES), AT_EXPAND(AT_BAREBONES_UNSIGNED_TYPES));

// After (method 2: use V2 integral types if AT_INTEGRAL_TYPES present)
AT_DISPATCH_V2(dtype, "op", AT_WRAP([&]() {
  kernel<scalar_t>();
}), AT_EXPAND(AT_INTEGRAL_TYPES_V2), AT_EXPAND(AT_FLOATING_TYPES));

Type group reference

Unsigned type groups:

  • AT_BAREBONES_UNSIGNED_TYPES: kUInt16, kUInt32, kUInt64
  • AT_INTEGRAL_TYPES_V2: AT_INTEGRAL_TYPES + AT_BAREBONES_UNSIGNED_TYPES

Relationship:

AT_INTEGRAL_TYPES          // kByte, kChar, kInt, kLong, kShort
AT_BAREBONES_UNSIGNED_TYPES  // kUInt16, kUInt32, kUInt64
AT_INTEGRAL_TYPES_V2       // INTEGRAL_TYPES + BAREBONES_UNSIGNED_TYPES

Instructions

Step 1: Determine if conversion to V2 is needed

Check if the file uses AT_DISPATCH_V2:

If using old AT_DISPATCH:

  • First convert to AT_DISPATCH_V2 using the at-dispatch-v2 skill
  • Then proceed with adding uint support

If already using AT_DISPATCH_V2:

  • Proceed directly to Step 2

Step 2: Analyze the current dispatch macro

Identify what type groups are currently in use:

AT_DISPATCH_V2(dtype, "op", AT_WRAP([&]() {
  // body
}), AT_EXPAND(AT_ALL_TYPES), kHalf, kBFloat16);
    ^^^^^^^^^^^^^^^^^^^^^^^^^
    Current type coverage

Common patterns:

  • AT_EXPAND(AT_ALL_TYPES) → includes AT_INTEGRAL_TYPES + AT_FLOATING_TYPES
  • AT_EXPAND(AT_INTEGRAL_TYPES) → signed integers only
  • AT_EXPAND(AT_FLOATING_TYPES) → floating point types

Step 3: Choose the uint addition method

Two approaches:

Method 1: Add AT_BAREBONES_UNSIGNED_TYPES explicitly

  • Use when: You want to be explicit about adding uint support
  • Add AT_EXPAND(AT_BAREBONES_UNSIGNED_TYPES) to the type list

Method 2: Substitute AT_INTEGRAL_TYPES with AT_INTEGRAL_TYPES_V2

  • Use when: The dispatch already uses AT_EXPAND(AT_INTEGRAL_TYPES)
  • More concise: replaces one type group with its superset
  • Only applicable if AT_INTEGRAL_TYPES is present

Step 4: Apply the transformation

Method 1 example:

// Before
AT_DISPATCH_V2(
    dtype,
    "min_values_cuda",
    AT_WRAP([&]() {
      kernel_impl<scalar_t>(iter);
    }),
    AT_EXPAND(AT_ALL_TYPES),
    kBFloat16, kHalf, kBool
);

// After (add unsigned types)
AT_DISPATCH_V2(
    dtype,
    "min_values_cuda",
    AT_WRAP([&]() {
      kernel_impl<scalar_t>(iter);
    }),
    AT_EXPAND(AT_ALL_TYPES),
    AT_EXPAND(AT_BAREBONES_UNSIGNED_TYPES),
    kBFloat16, kHalf, kBool
);

Method 2 example:

// Before
AT_DISPATCH_V2(
    dtype,
    "integral_op",
    AT_WRAP([&]() {
      kernel<scalar_t>();
    }),
    AT_EXPAND(AT_INTEGRAL_TYPES)
);

// After (substitute with V2)
AT_DISPATCH_V2(
    dtype,
    "integral_op",
    AT_WRAP([&]() {
      kernel<scalar_t>();
    }),
    AT_EXPAND(AT_INTEGRAL_TYPES_V2)
);

Step 5: Handle AT_ALL_TYPES vs individual type groups

If the dispatch uses AT_EXPAND(AT_ALL_TYPES):

  • AT_ALL_TYPES = AT_INTEGRAL_TYPES + AT_FLOATING_TYPES
  • To add uint: add AT_EXPAND(AT_BAREBONES_UNSIGNED_TYPES) to the list

If the dispatch separately lists INTEGRAL and FLOATING:

// Before
AT_EXPAND(AT_INTEGRAL_TYPES), AT_EXPAND(AT_FLOATING_TYPES)

// After (Method 2 preferred)
AT_EXPAND(AT_INTEGRAL_TYPES_V2), AT_EXPAND(AT_FLOATING_TYPES)

Step 6: Verify all dispatch sites

Check the file for ALL dispatch macros that need uint support:

  • Some operators have multiple dispatch sites (CPU, CUDA, different functions)
  • Apply the transformation consistently across all sites
  • Ensure each gets the same type coverage updates

Step 7: Validate the changes

Check that:

  • AT_DISPATCH_V2 format is used (not old AT_DISPATCH)
  • Unsigned types are added via one of the two methods
  • All relevant dispatch sites in the file are updated
  • Type groups use AT_EXPAND()
  • Arguments are properly formatted and comma-separated

Common patterns

Pattern 1: AT_ALL_TYPES + extras

// Before
AT_DISPATCH_V2(dtype, "op", AT_WRAP([&]() {
  kernel<scalar_t>();
}), AT_EXPAND(AT_ALL_TYPES), kHalf, kBFloat16);

// After
AT_DISPATCH_V2(dtype, "op", AT_WRAP([&]() {
  kernel<scalar_t>();
}), AT_EXPAND(AT_ALL_TYPES), AT_EXPAND(AT_BAREBONES_UNSIGNED_TYPES), kHalf, kBFloat16);

Pattern 2: Separate INTEGRAL + FLOATING

// Before
AT_DISPATCH_V2(dtype, "op", AT_WRAP([&]() {
  kernel<scalar_t>();
}), AT_EXPAND(AT_INTEGRAL_TYPES), AT_EXPAND(AT_FLOATING_TYPES));

// After
AT_DISPATCH_V2(dtype, "op", AT_WRAP([&]() {
  kernel<scalar_t>();
}), AT_EXPAND(AT_INTEGRAL_TYPES_V2), AT_EXPAND(AT_FLOATING_TYPES));

Pattern 3: Old dispatch needs conversion first

// Before (needs v2 conversion first)
AT_DISPATCH_ALL_TYPES_AND2(kHalf, kBFloat16, dtype, "op", [&]() {
  kernel<scalar_t>();
});

// After v2 conversion
AT_DISPATCH_V2(dtype, "op", AT_WRAP([&]() {
  kernel<scalar_t>();
}), AT_EXPAND(AT_ALL_TYPES), kHalf, kBFloat16);

// After adding uint support
AT_DISPATCH_V2(dtype, "op", AT_WRAP([&]() {
  kernel<scalar_t>();
}), AT_EXPAND(AT_ALL_TYPES), AT_EXPAND(AT_BAREBONES_UNSIGNED_TYPES), kHalf, kBFloat16);

Multiple dispatch sites example

For a file with multiple functions:

void min_values_kernel_cuda(TensorIterator& iter) {
  AT_DISPATCH_V2(iter.dtype(), "min_values_cuda", AT_WRAP([&]() {
    impl<scalar_t>(iter);
  }), AT_EXPAND(AT_ALL_TYPES), AT_EXPAND(AT_BAREBONES_UNSIGNED_TYPES), kBFloat16, kHalf);
  //                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  //                           Added uint support
}

void min_launch_kernel(TensorIterator &iter) {
  AT_DISPATCH_V2(iter.input_dtype(), "min_cuda", AT_WRAP([&]() {
    gpu_reduce_kernel<scalar_t>(iter);
  }), AT_EXPAND(AT_ALL_TYPES), AT_EXPAND(AT_BAREBONES_UNSIGNED_TYPES), kBFloat16, kHalf);
  //                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  //                           Added uint support here too
}

Decision tree

Use this decision tree to determine the approach:

Is the file using AT_DISPATCH_V2?
├─ No → Use at-dispatch-v2 skill first, then continue
└─ Yes
   └─ Does it use AT_EXPAND(AT_INTEGRAL_TYPES)?
      ├─ Yes → Replace with AT_EXPAND(AT_INTEGRAL_TYPES_V2)
      └─ No → Add AT_EXPAND(AT_BAREBONES_UNSIGNED_TYPES) to type list

Edge cases

Case 1: Dispatch with only floating types

If the operator only supports floating point types, don't add uint support:

// Leave as-is - floating point only operator
AT_DISPATCH_V2(dtype, "float_op", AT_WRAP([&]() {
  kernel<scalar_t>();
}), AT_EXPAND(AT_FLOATING_TYPES), kHalf);

Case 2: Complex types present

Unsigned types work alongside complex types:

AT_DISPATCH_V2(dtype, "op", AT_WRAP([&]() {
  kernel<scalar_t>();
}), AT_EXPAND(AT_ALL_TYPES),
    AT_EXPAND(AT_BAREBONES_UNSIGNED_TYPES),
    AT_EXPAND(AT_COMPLEX_TYPES),
    kHalf, kBFloat16);

Case 3: Already has uint support

Check if uint types are already present:

  • If AT_INTEGRAL_TYPES_V2 is used → already has uint support
  • If AT_BAREBONES_UNSIGNED_TYPES is already in list → already has uint support
  • Skip the file if uint support is already present

Workflow

When asked to add uint support:

  1. Read the target file
  2. Check if using AT_DISPATCH_V2:
    • If not → use at-dispatch-v2 skill first
  3. Identify all dispatch macro sites
  4. For each dispatch:
    • Analyze current type groups
    • Choose method (add BAREBONES_UNSIGNED or upgrade to V2)
    • Apply transformation with Edit tool
  5. Show the user the changes
  6. Explain what was modified

Important notes

  • Always check if v2 conversion is needed first
  • Apply changes consistently across all dispatch sites in the file
  • Method 2 (AT_INTEGRAL_TYPES_V2) is cleaner when applicable
  • Method 1 (explicit AT_BAREBONES_UNSIGNED_TYPES) is more explicit
  • Unsigned types are: kUInt16, kUInt32, kUInt64 (not kByte which is uint8)
  • Some operators may not semantically support unsigned types - use judgment

Testing

After adding uint support, the operator should accept uint16, uint32, and uint64 tensors. The user is responsible for functional testing.

pytorch의 다른 스킬

zephyr
pytorch
임베디드 보드용 Zephyr RTOS 모듈로 ExecuTorch를 빌드하고 구성합니다. ET로 Zephyr 워크스페이스를 설정하거나 보드 지원(오버레이 등)을 추가할 때 사용합니다.
aoti-debug
pytorch
AOTInductor(AOTI) 오류 및 충돌을 디버깅합니다. AOTI 세그폴트, 장치 불일치 오류, 상수 로딩 실패 또는 런타임 오류가 발생할 때 사용하세요.
skill-writer
pytorch
Claude Code를 위한 잘 구조화된 Agent Skill 생성 가이드로, 모범 사례와 검증을 포함합니다. Skill의 전체 수명 주기(범위 설정, 파일 구조, YAML 프론트매터 검증, 콘텐츠 구성, 테스트 절차)를 다룹니다. 엄격한 명명 규칙(소문자, 하이픈, 최대 64자)과 설명 요구 사항(특정 트리거, 파일 유형, "무엇" 및 "언제" 절)을 적용합니다. 읽기 전용 Skill, 스크립트 기반 Skill, 다중 파일 Skill 등 일반적인 패턴에 대한 템플릿을 제공합니다.
triaging-issues
pytorch
GitHub 이슈를 분류하여 온콜 팀에 라우팅하고, 레이블을 적용하며, 질문을 종료합니다. 새로운 PyTorch 이슈를 처리하거나 이슈 분류를 요청받았을 때 사용하세요.
wheel-size-analyzer
pytorch
PyTorch nightly wheel 크기를 GitHub Actions 아티팩트 API를 사용하여 날짜 범위에 걸쳐 분석합니다. 바이너리 크기 변경 추적, wheel 크기 식별에 사용합니다…
release-go-live-binary-build-matrix
pytorch
tools/scripts/generate_binary_build_matrix.py를 PyTorch 릴리스가 라이브될 때 업데이트합니다. CURRENT_STABLE_VERSION을 새로운 안정 버전으로 올리고, 해당…
pr-review
pytorch
PyTorch 풀 리퀘스트의 코드 품질, 테스트 커버리지, 보안 및 하위 호환성을 검토합니다. PR을 검토할 때, 코드 변경 사항을 검토하도록 요청받았을 때 사용합니다.
qualcomm
pytorch
QNN(Qualcomm AI Engine Direct) 백엔드를 빌드, 테스트 또는 개발합니다. backends/qualcomm/에서 작업하거나 QNN을 빌드할 때 사용합니다(계속…).