# NVIDIA/cutlass v4.6.0: CUTLASS 4.6.0 — retained record

> Retained github record from github:NVIDIA/cutlass.

Canonical: https://highsignal.app/data/records/8990f3569c3f8e16

[← sources](https://highsignal.app/data)


source: [github](https://highsignal.app/data/github) (github:NVIDIA/cutlass)  published 2026-07-13 19:28 ingested 2026-07-14 07:51

[NVIDIA Corporation](https://highsignal.app/entities/NVDA)[original source ↗](https://github.com/NVIDIA/cutlass/releases/tag/v4.6.0)

## retained text



```
* Release [documentation](https://docs.nvidia.com/cutlass/latest/media/docs/cpp/gemm_performance_measurement_methodology_guidelines.md) that explains how to accurately profiling GEMM performance.

### CuTe DSL
* New features
  - New fine-grained compilation API: cute.compile_to that gives control over the what stage the compiler outputs. This feature allows customization of the path from compilation to runtime execution. cute.compile_to is considered experimental in 4.6.
  - Experimental Feature: Added the IKET (In-Kernel-Event-Tracing) profiler for instrumentation-based intra-kernel activities tracing.  This enables fine-grained profiling and makes it easier to understand persistent, warp-specialized kernels' performance.  This is a beta feature provided by CUTLASS Python until a NVIDIA DevTools product is released, there is no guarantee that this interface will remain stable!
  - Distribute compiler binaries to accompany cute.compile_to allowing users to build customized compile-execute pipelines outside of Python. Both static and shared compiler and executor/runtime libraries will be provided. Compiler binaries will be uploaded to GitHub with each release.
  - Supported AoT cross-compilation for aarch64-linux-gnu
  - Support for two launch attributes: launch completion events (cudaLaunchAttributeLaunchCompletionEvent), for recording an event once all thread blocks have begun executing, and launch programmatic events (cudaLaunchAttributeProgrammaticEvent), for PDL event-based synchronization
  - Supported auto calculating per-kernel shared memory carveout preference, or use new launch option `preferred_smem_carveout` to set manually.
  - Auto-deduced smem size for launching kernels
    - Launch config `smem` now defaults to `None` for auto-calculating kernel shared memory usage, which is recommended unless manual control is required.
    - Warnings will be raised when the manually set shared memory size is insufficient or exceeds the GPU maximum.
    - The default shared memory usage calculation aligns with CUDA C++ static shared memory behavior, i.e. summing all allocations additively.
    - An additional launch option `smem_merge_branch_allocs` is provided to merge shared memory allocations across mutually exclusive code branches, which is recommended for inlined mega-kernels to reduce total footprint.
  - SASS dumping in DSL is now supported in a self-contained manner - no CUDA toolkit installation required to get nvdisasm 

* Bug fixing and improvements
  - Add the missing elect_one in cute.copy for bulk copy.
    - The elect_one required for async bulk copy was missing in cute.copy. It's now generated in cute.copy automatically.
    - Nesting elect_one will cause functionality issues. Please remove elect_one around cute.copy with async bulk copy.
    - Elect_one around direct async bulk copy instruction should be kept as it bypasses the cute.copy layer and will not be affected by this fix.
    - Affected copy atoms are CopyBulkG2SOp, CopyBulkG2SMulticastOp, CopyBulkS2GOp, CopyBulkS2GByteMaskOp, and CopyBulkS2SOp.
    - An Example showing changes to avoid nesting `elect_one` could be found in this [PR](https://github.com/Dao-AILab/quack/pull/164)
  - Improvements on linter support with more type ignores cleaned up
  - Improvements on tvm-ffi CUDA runtime error diagnostics
  - Improvements on dataclass support for TVM-FFI
  - Fixed a regression on compilation time
  - Enhancement on compile time checks to reject mis-aligned smem operand for TMA
  - Long-deprecated API clean-up, including:
    - cute.core.ThrMma, please use cute.ThrMma instead
    - cute.core.ThrCopy, please use cute.ThrCopy instead
    - cute.make_fragment, please use cute.make_rmem_tensor instead
  - Fixed following issues
    - https://github.com/NVIDIA/cutlass/issues/3132
    - https://github.com/NVIDIA/cutlass/issues/3170
    - https://github.com/NVIDIA/cutlass/issues/3259
    - https://github.com/NVIDIA/cutlass/issues/3290
    - https://github.com/NVIDIA/cutlass/issues/3298
    - https://github.com/NVIDIA/cutlass/issues/3312
    - https://github.com/NVIDIA/cutlass/issues/3327
    - https://github.com/NVIDIA/cutlass/issues/3329
    - https://github.com/NVIDIA/cutlass/issues/3342
    - https://github.com/NVIDIA/cutlass/issues/3348

### CUTLASS Operator API
* CUTLASS Operator API is a new addition to the CUTLASS Python stack, providing easy interfaces
to discover CUTLASS Python DSL kernels & integrate them in your code.
  - `pip install nvidia-cutlass-operators` to get started
* [Operator API Overview](https://docs.nvidia.com/cutlass/latest/media/docs/operators/overview.html)
  - See [currently supported kernels](https://docs.nvidia.com/cutlass/latest/media/docs/operators/overview.html#supported-and-upcoming-features)
* [Basic GEMM tutorial](https://docs.nvidia.com/cutlass/latest/media/docs/operators/tutorials/000_gemm.html)
  - More tutorials [here](https://docs.nvidia.com/cutlass/latest/media/docs/operators/tutorials/index.html)
* [GitHub source](https://github.com/NVIDIA/cutlass/tree/main/operators)
* [API Reference](https://docs.nvidia.com/cutlass/latest/media/docs/operators/api_reference/index.html)

### CUTLASS C++
* Add [example 113](https://github.com/NVIDIA/cutlass/tree/main/examples/113_hopper_gemm_activation_fusion) for Hopper GEMM with activation fusion.
  - Supports standard and gated activations (e.g., SiLu) with fp8 and fp16 inputs.
  - Covers both regular GEMM and grouped GEMM variants.
* Improve SM90 grouped/ptr-array GEMM with EVT support.
  - Adds the EVT (Epilogue Visitor Tree) plumbing required to do activation, bias, and auxiliary-tensor fusion inside SM90 grouped and ptr-array GEMM kernels.
* Add ptr-array TMA collective for tensor/token-scaled FP8 grouped GEMM Blackwell SM120/SM121 kernels.
  - Implement `CollectiveMma` and `CollectiveBuilder` specializations for `MainloopSm120ArrayTmaWarpSpecialized`, enabling ptr-array grouped GEMM (MoE expert dispatch) with tensor- and token-level FP8 scaling.
  - Corresponding [unit test](https://github.com/NVIDIA/cutlass/tree/main/test/unit/gemm/device/sm120_tensorop_gemm/sm120_gemm_f8_f8_f32_tensor_op_group_gemm.cu) 
* Add tileN = 8,16 for Blackwell SM120 blockscale GEMM kernels.
* Fix `DescriptorIterator::operator+` in `mma_traits_sm100.hpp` to use 32-bit arithmetic on CUDA toolkit version <= 13.3, preserving the high half of the smem descriptor.
* Fix a CUDA structured bindings header issue.
* Various improvements and fixes from the community and CUTLASS team. Thanks to everyone who submitted PRs!
* Optimal code generation with CUDA toolkit versions 13.3.
```



document fetched 2026-07-20 08:43
