[PR #206] [MERGED] Fix syntax errors and correct the conditional statements #291

New issue

Closed

opened 2026-10-26 21:15:52 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-26 21:15:52 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepGEMM/pull/206
Author: @FlamingoPg
Created: 10/1/2025
Status: ✅ Merged
Merged: 10/1/2025
Merged by: @LyricZhao

Base: main ← Head: main

📝 Commits (1)

c4fb1d5 Fix syntax errors and correct the conditional statements

📊 Changes

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

View changed files

📝 deep_gemm/include/deep_gemm/common/sm90_utils.cuh (+2 -2)

📄 Description

As titled, we dont need to assert cuda version > cu 12.5

#if ((__CUDACC_VER_MAJOR__ > 12) or ((__CUDACC_VER_MAJOR__ == 12) and (__CUDACC_VER_MINOR__ >= 5)))
    asm volatile("tensormap.replace.tile.global_stride.shared::cta.b1024.b64 [%0], 0, %1;" :: "l"(smem_int_desc), "l"(new_stride));

Ref: https://docs.nvidia.com/cuda/archive/12.3.0/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-tensormap-replace

_{🔄 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/206 **Author:** [@FlamingoPg](https://github.com/FlamingoPg) **Created:** 10/1/2025 **Status:** ✅ Merged **Merged:** 10/1/2025 **Merged by:** [@LyricZhao](https://github.com/LyricZhao) **Base:** `main` ← **Head:** `main` --- ### 📝 Commits (1) - [`c4fb1d5`](https://github.com/deepseek-ai/DeepGEMM/commit/c4fb1d5830fe93cfa9da2602b63d1a33ecf127c7) Fix syntax errors and correct the conditional statements ### 📊 Changes **1 file changed** (+2 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `deep_gemm/include/deep_gemm/common/sm90_utils.cuh` (+2 -2) </details> ### 📄 Description As titled, we dont need to assert cuda version > cu 12.5 ```cuda #if ((__CUDACC_VER_MAJOR__ > 12) or ((__CUDACC_VER_MAJOR__ == 12) and (__CUDACC_VER_MINOR__ >= 5))) asm volatile("tensormap.replace.tile.global_stride.shared::cta.b1024.b64 [%0], 0, %1;" :: "l"(smem_int_desc), "l"(new_stride)); ``` Ref: https://docs.nvidia.com/cuda/archive/12.3.0/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-tensormap-replace --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-26 21:15:52 +00:00

closed this issue
added the
pull-request
label

No labels

pull-request

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

deepseek-ai/DeepGEMM#291

No description provided.

Rows
Columns