Skip to content

Dev/cloud - #10

Merged
Ra4ster merged 3 commits into
dev/CUDAfrom
dev/Cloud
Sep 24, 2026
Merged

Ra4ster merged 3 commits into
dev/CUDAfrom
dev/Cloud

Conversation

@Ra4ster

@Ra4ster Ra4ster commented Sep 24, 2026

Copy link
Copy Markdown
Owner

Description

Fixed CUDA hardcoded architecture bug, found a bug in the CUDABackend.cu file leading to kernel image errors, and proved a successful build on Ohio Supercomputer Center.

Closes Dev/Cloud

Type of change

  • Bug fix
  • New feature
  • Performance improvement
  • Documentation
  • Build/tooling
  • Breaking change (existing C++ or Python API behavior changes)

Platform(s) and compiler(s) tested:

RHEL Linux, IPCX (failed), + GCC

Performance impact

<1s on MNIST. In general it is now building though.

@Ra4ster
Ra4ster merged commit 73c646f into dev/CUDA Sep 24, 2026
1 check failed
@Ra4ster
Ra4ster deleted the dev/Cloud branch September 24, 2026 00:15
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant