New to Claude Skills? Learn how to install them →

Apytorch on GitHub

Add Unsigned Integer Support

Free

Integrate unsigned integer types in PyTorch operators.

by pytorch102.3k stars on pytorch/pytorch
1 views
Updated Aug 10, 2026
Get this skill

Free · Opens the source repo

What Add Unsigned Integer Support does

The Add Unsigned Integer Support skill facilitates the inclusion of unsigned integer types (uint16, uint32, uint64) in PyTorch operators by modifying the AT_DISPATCH macros. This skill is essential for developers who need to extend the type coverage of PyTorch's computational capabilities, particularly when dealing with unsigned integer data types in their machine learning models or custom operations.

When you are working on PyTorch extensions or custom kernels, you may encounter scenarios where unsigned integer support is necessary. This skill provides a structured approach to update existing operator implementations, ensuring that they can handle uint types effectively. By following the provided instructions, developers can seamlessly integrate uint support into their code, enhancing the versatility and performance of their applications.

The skill outlines a step-by-step process for identifying whether the existing code uses the older AT_DISPATCH macros or the newer AT_DISPATCH_V2. It then guides users through analyzing the current dispatch macros and selecting the appropriate method to add uint support. This ensures that all relevant dispatch sites are updated consistently, maintaining the integrity of the codebase while expanding its functionality.

This skill is particularly beneficial for developers working on numerical computations, image processing, or any domain where unsigned integers are relevant. It empowers them to leverage the full potential of PyTorch by enabling support for additional data types, thus broadening the scope of operations that can be performed efficiently.

When to use it

Use this skill when adding support for uint16, uint32, or uint64 types to PyTorch operators and kernels.

When not to use it

This skill is not suitable for scenarios where unsigned integer support is not required or when working with older versions of PyTorch that do not utilize AT_DISPATCH_V2.

What you can build with it

Adding uint support to a custom operator

When implementing a new operator that requires unsigned integer types, this skill guides you through the necessary macro updates.

Updating existing kernels for expanded type coverage

If you have existing kernels that need to handle unsigned integers, this skill provides the steps to modify them appropriately.

Enhancing data handling in machine learning models

For machine learning applications that utilize unsigned integers, this skill enables the necessary support in PyTorch operations.

How to install Add Unsigned Integer Support

View source

1. Install with the skills CLI

npx skills add pytorch/pytorch/add-uint-support --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by pytorch

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.

Frequently asked questions about Add Unsigned Integer Support

Similar skills