[PR #65] [MERGED] Fix get_col_major_tma_aligned_tensor to handle 2-dimensional inputs #227

New issue

Closed

opened 2026-10-26 21:15:04 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-26 21:15:04 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepGEMM/pull/65
Author: @Z-NAVY
Created: 3/13/2025
Status: ✅ Merged
Merged: 3/14/2025
Merged by: @soundOfDestiny

Base: main ← Head: main

📝 Commits (1)

3f92607 Fix get_col_major_tma_aligned_tensor to handle 2-dimensional inputs

📊 Changes

1 file changed (+5 additions, -2 deletions)

View changed files

📝 deep_gemm/jit_kernels/utils.py (+5 -2)

📄 Description

When the input is two-dimensional and satisfies both column-major order alignment and TMA alignment, it should be returned directly instead of undergoing further processing, as such handling would be redundant and introduce unnecessary D2D operations.

github.com/Z-NAVY/DeepGEMM@3f92607b98

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/DeepGEMM/pull/65 **Author:** [@Z-NAVY](https://github.com/Z-NAVY) **Created:** 3/13/2025 **Status:** ✅ Merged **Merged:** 3/14/2025 **Merged by:** [@soundOfDestiny](https://github.com/soundOfDestiny) **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (1) - [`3f92607`](https://github.com/deepseek-ai/DeepGEMM/commit/3f92607b981fe6ae8537dc9d7b2b9972751bc280) Fix get_col_major_tma_aligned_tensor to handle 2-dimensional inputs ### 📊 Changes **1 file changed** (+5 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `deep_gemm/jit_kernels/utils.py` (+5 -2) </details> ### 📄 Description When the input is two-dimensional and satisfies both column-major order alignment and TMA alignment, it should be returned directly instead of undergoing further processing, as such handling would be redundant and introduce unnecessary D2D operations. https://github.com/Z-NAVY/DeepGEMM/commit/3f92607b981fe6ae8537dc9d7b2b9972751bc280 --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-26 21:15:04 +00:00