NVIDIA / NVIDIA/cutlass

[FEA] When sm < 90, no CUTLASS 3.0 GEMM templates

Open
#2,210 5 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

add CUTLASS 3.0 GEMM templates for sm < 90
resolve no suitable Cutlass GEMM configs for max-autotune mode issue https://github.com/pytorch/pytorch/issues/150314

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

Start by tracing the CUTLASS 3.0 GEMM template and configuration paths for architectures below sm 90, then review the linked PyTorch issue for the max-autotune failure context. Done means suitable CUTLASS GEMM configurations are available for sm < 90 and the reported no-suitable-configurations case is resolved.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
performance
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.