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

Fix JIT tests

Browse Source
This commit is contained in:
Chenggang Zhao
2025-05-16 14:39:58 +08:00
parent 78d8362e7a
commit 391755ada0
6 changed files with 14 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
deep_gemm/jit_kernels/wgrad_gemm.py
View File

@@ -110,7 +110,7 @@ def wgrad_gemm_fp8_fp8_fp32_nt(lhs: Tuple[torch.Tensor, torch.Tensor],
# Generate, build and run the kernel
code = FP8WGradGemmRuntime.generate(kwargs)
runtime = build('wgrad_gemm_fp8_fp8_fp32_nt', code, FP8WGradGemmRuntime, kwargs)
runtime(kwargs)
runtime(**kwargs)
def k_grouped_wgrad_gemm_fp8_fp8_fp32_nt(lhs: Tuple[torch.Tensor, torch.Tensor],