Skip to content

Remove definition that causes error in cuda 12.6 #7191

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Remove definition that causes error in cuda 12.6 #7191

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fbaacf3
Remove definition that causes error in cuda 12.6
loadams Mar 31, 2025
f66296d
Merge branch 'master' into loadams/cuda-compilation-nv-bfloat162
loadams Apr 4, 2025
989fb61
Merge branch 'master' into loadams/cuda-compilation-nv-bfloat162
hwchen2017 Apr 10, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 0 additions & 5 deletions csrc/transformer/inference/csrc/gelu.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,11 +11,6 @@ namespace cg = cooperative_groups;
#define MAX_CAP 4
#define MAX_SEQ 2048

// only used to avoid compilation error due to lack of definition.
#ifndef BF16_AVAILABLE
using __nv_bfloat162 = __half2;
#endif

inline __device__ float gelu(const float x)
{
constexpr float sqrt_param = 0.79788456080286535587989211986876f;
Expand Down
5 changes: 0 additions & 5 deletions csrc/transformer/inference/csrc/transform.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,11 +10,6 @@
#include "inference_cuda_layers.h"
namespace cg = cooperative_groups;

// only used to avoid compilation error due to lack of definition.
#ifndef BF16_AVAILABLE
using __nv_bfloat162 = __half2;
#endif

// Bias add

__global__ void bias_add_transform_0213(float* output,
Expand Down
Loading