DeepSeek/DeepGEMM
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepGEMM synced 2025-06-26 23:15:49 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

feat: compat for old drivers

Browse Source 
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
This commit is contained in:
Zihua Wu
2025-04-22 20:42:59 -07:00
parent 78c7fa347e
commit 767793bf95
3 changed files with 61 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
deep_gemm/jit/template.py
View File

@@ -22,7 +22,9 @@ def generate(**kwargs: Dict[str, Any]) -> str:
#include <cuda_fp8.h>
#include <deep_gemm/fp8_gemm.cuh>
namespace deep_gemm {{
using namespace deep_gemm;
#ifndef NVRTC_JIT_COMPILATION
__global__ void dummy_kernel() {{
void *ptr = (void *)&fp8_gemm_kernel<
{kwargs['N']},
@@ -41,7 +43,7 @@ __global__ void dummy_kernel() {{
GemmType::{kwargs['GEMM_TYPE']}
>;
}}
}}
#endif
'''
# Debug print