Skip to content

Clean up quantized matmul condition code#9506

Merged
vanbasten23 merged 1 commit intopytorch:masterfrom
kyuyeunk:fix_w8a8_kernel_numeric
Jul 24, 2025
Merged

Clean up quantized matmul condition code#9506
vanbasten23 merged 1 commit intopytorch:masterfrom
kyuyeunk:fix_w8a8_kernel_numeric

Conversation

@kyuyeunk
Copy link
Copy Markdown
Contributor

@kyuyeunk kyuyeunk commented Jul 24, 2025

Clean up condition code to make it easier to understand the behavior.

@kyuyeunk kyuyeunk closed this Jul 24, 2025
Comment thread torch_xla/experimental/pallas_kernels/quantized_matmul_kernel.py Outdated
@kyuyeunk kyuyeunk reopened this Jul 24, 2025
@vanbasten23
Copy link
Copy Markdown
Collaborator

Could you also change the PR title?

@kyuyeunk kyuyeunk force-pushed the fix_w8a8_kernel_numeric branch from fb9b3fd to f84c5c1 Compare July 24, 2025 17:52
Clean up condition code to make it easier to understand the behavior.
@kyuyeunk kyuyeunk force-pushed the fix_w8a8_kernel_numeric branch from f84c5c1 to 84dc1f0 Compare July 24, 2025 17:54
@kyuyeunk kyuyeunk changed the title Fix w8a8 kernel numeric Clean up quantized matmul condition code Jul 24, 2025
@kyuyeunk
Copy link
Copy Markdown
Contributor Author

Could you also change the PR title?

Done.

Copy link
Copy Markdown
Collaborator

@vanbasten23 vanbasten23 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks Kyuyeun

@vanbasten23 vanbasten23 merged commit 16b1202 into pytorch:master Jul 24, 2025
23 of 24 checks passed
@kyuyeunk kyuyeunk deleted the fix_w8a8_kernel_numeric branch August 10, 2025 20:37
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.

2 participants