EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Fix deepseek-v3 with torch.compile in PyTorch 2.6. (#5213)

Browse Source
This commit is contained in:
Richard Zou
2025-04-10 12:14:38 -04:00
committed by GitHub
parent 1078396f47
commit 76f44c2a8d
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
sgl-kernel/csrc/common_extension.cc
View File

@@ -177,7 +177,8 @@ TORCH_LIBRARY_FRAGMENT(sgl_kernel, m) {
*/ */
m.def( m.def(
"bmm_fp8(Tensor A, Tensor B, Tensor! D, Tensor A_scale, Tensor B_scale, Tensor workspace_buffer, int " "bmm_fp8(Tensor A, Tensor B, Tensor! D, Tensor A_scale, Tensor B_scale, Tensor workspace_buffer, int "
"cublas_handle, int cuda_stream) -> ()"); "cublas_handle, int cuda_stream) -> ()",
{at::Tag::needs_fixed_stride_order});
m.impl("bmm_fp8", torch::kCUDA, &bmm_fp8); m.impl("bmm_fp8", torch::kCUDA, &bmm_fp8);
m.def( m.def(