NVIDIA / NVIDIA/cutlass

[QST] On sm1xx, fp16 and fp8 per tensor scale gemm must be align to 128bit or not?

Open
#2,863 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

? - Needs Triage inactive-30d inactive-90d question
Dominant language
C++
Stars
10.5k
Forks
2.1k
Avg merge
3d 11h
Merged PRs (30d)
7

Description

What is your question?
Hi.
I am using cutlass to compute fp16 gemm and fp8 per tensor scale gemm on sm1xx.
With cutlass old version, it seems A/B/C/D must be align to 128bit.
I would like to know the requirements with latest 4.3.2.

Thanks for your reply.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The payload names no source file or test. Start by comparing CUTLASS 4.3.2 documentation and examples for fp16 and fp8 per-tensor-scale GEMM on sm1xx with the reported old-version behavior. Done means a maintainer-confirmed statement of whether A/B/C/D require 128-bit alignment.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
performance
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.