# NVIDIA/cutlass v4.5.1: CUTLASS 4.5.1 — retained record

> Retained github record from github:NVIDIA/cutlass.

Canonical: https://highsignal.app/data/records/becc3d33f160c896

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


source: [github](https://highsignal.app/data/github) (github:NVIDIA/cutlass)  published 2026-05-27 02:31 ingested 2026-05-27 09:11

[NVIDIA Corporation](https://highsignal.app/entities/NVDA)[original source ↗](https://github.com/NVIDIA/cutlass/releases/tag/v4.5.1)

## extract

## CuTe DSL
* Bug fixing and improvements
  - Fixed following issues:
    https://github.com/NVIDIA/cutlass/issues/3219
    https://github.com/NVIDIA/cutlass/issues/3218
    https://github.com/NVIDIA/cutlass/issues/3212
    https://github.com/NVIDIA/cutlass/issues/3210
    https://github.com/NVIDIA/cutlass/issues/3208
    https://github.com/NVIDIA/cutlass/issues/3201
    https://github.com/NVIDIA/cutlass/issues/3227
  - Fixed Jax int64 stride divisibility issue
  - Fixed issues for SM120 blockscaled MMAs
	- added missing MXFP8MMAOP and MXF8F6F4MMAOP for sm120.

## CUTLASS C++
* Fix SM100 F8F6F4 SS MMA (1SM and 2SM) traits to use typed op templates.
* Add UE8M0 (uniform exponent distribution) initialization support in tensor fill utilities.
* Add `cvt.rn.bf16x2.e4m3x2` conversion instruction support to `numeric_conversion.h`.
* Update [example 93](https://github.com/NVIDIA/cutlass/tree/main/examples/93_blackwell_low_latency_gqa) with paged KV cache support for Blackwell low-latency GQA.

## retained text

No document body was retained for this record — only its metadata was stored.
