[PR #238] [MERGED] fix: k_grouped_fp8_gemm_nt_contiguous crashes with n = 768 on H100 #303

New issue

Closed

opened 2026-10-26 21:16:03 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-26 21:16:03 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepGEMM/pull/238
Author: @xinqiu
Created: 12/5/2025
Status: ✅ Merged
Merged: 2/25/2026
Merged by: @zheanxu

Base: main ← Head: fix/k_grouped_fp8

📝 Commits (1)

7cd9c4b fix: k_grouped_fp8_gemm_nt_contiguous crashes with n = 768 on H100

📊 Changes

1 file changed (+35 additions, -5 deletions)

View changed files

📝 deep_gemm/include/deep_gemm/impls/sm90_fp8_gemm_1d1d.cuh (+35 -5)

📄 Description

_{🔄 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/238 **Author:** [@xinqiu](https://github.com/xinqiu) **Created:** 12/5/2025 **Status:** ✅ Merged **Merged:** 2/25/2026 **Merged by:** [@zheanxu](https://github.com/zheanxu) **Base:** `main` ← **Head:** `fix/k_grouped_fp8` --- ### 📝 Commits (1) - [`7cd9c4b`](https://github.com/deepseek-ai/DeepGEMM/commit/7cd9c4b5ae36f9bdc9eff190ba0abc4653a25689) fix: k_grouped_fp8_gemm_nt_contiguous crashes with n = 768 on H100 ### 📊 Changes **1 file changed** (+35 additions, -5 deletions) <details> <summary>View changed files</summary> 📝 `deep_gemm/include/deep_gemm/impls/sm90_fp8_gemm_1d1d.cuh` (+35 -5) </details> ### 📄 Description <img width="1248" height="252" alt="image" src="https://github.com/user-attachments/assets/ea9fa8dd-55bb-496c-9299-be21a7874905" /> --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-26 21:16:03 +00:00