Skip to content

[Common] Move arch specific helpers in ptx.cuh to a new header #3392

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
kainzhong wants to merge 4 commits into
base: main
Choose a base branch
from
Open

[Common] Move arch specific helpers in ptx.cuh to a new header #3392

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
7ee52e2
[Common] Make ptx.cuh arch agnoistic by moving arch specific helpers …
kainzhong Aug 17, 2026
41424b9
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Aug 17, 2026
0b21a82
whoops
kainzhong Aug 17, 2026
9d74243
Update transformer_engine/common/util/ptx.cuh
kainzhong Aug 18, 2026
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
2 changes: 1 addition & 1 deletion transformer_engine/common/cast/mxfp8/gated_mxfp8.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@

#include "../../common.h"
#include "../../util/math.h"
#include "../../util/ptx.cuh"
#include "../../util/ptx_arch_spec.cuh"
#include "../../utils.cuh"
#include "swizzle.cuh"

Expand Down
2 changes: 1 addition & 1 deletion transformer_engine/common/cast/mxfp8/group_quantize_mxfp8.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@
#include "../../common.h"
#include "../../util/cuda_runtime.h"
#include "../../util/math.h"
#include "../../util/ptx.cuh"
#include "../../util/ptx_arch_spec.cuh"
#include "../../utils.cuh"
#include "../core/common.cuh"
#include "swizzle.cuh"
Expand Down
2 changes: 1 addition & 1 deletion transformer_engine/common/cast/mxfp8/quantize_mxfp8.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@

#include "../../common.h"
#include "../../util/math.h"
#include "../../util/ptx.cuh"
#include "../../util/ptx_arch_spec.cuh"
#include "../../utils.cuh"
#include "../core/common.cuh"
#include "specialized/quantize_mxfp8.cuh"
Expand Down
2 changes: 1 addition & 1 deletion transformer_engine/common/cast/mxfp8/specialized/quantize_mxfp8.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@

#include <cstdlib>

#include "../../../util/ptx.cuh"
#include "../../../util/ptx_arch_spec.cuh"
#include "../swizzle.cuh" // gemm_swizzled_scale_idx (parent dir, GEMM scale swizzle)
#include "state_counter.cuh"
#include "swizzle.cuh" // specialized/swizzle.cuh (TMA input bank-conflict swizzle)
Expand Down
2 changes: 1 addition & 1 deletion transformer_engine/common/cast/nvfp4/group_quantize_transpose_nvfp4.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@

#include "../../common.h"
#include "../../util/math.h"
#include "../../util/ptx.cuh"
#include "../../util/ptx_arch_spec.cuh"
#include "../../utils.cuh"
#include "core_nvfp4.cuh"

Expand Down
2 changes: 1 addition & 1 deletion transformer_engine/common/cast/nvfp4/quantize_transpose_nvfp4.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@

#include "../../common.h"
#include "../../util/math.h"
#include "../../util/ptx.cuh"
#include "../../util/ptx_arch_spec.cuh"
#include "../../utils.cuh"
#include "core_nvfp4.cuh"
#include "specialized/quantize_transpose_nvfp4_tuned_1D.cuh"
Expand Down
2 changes: 1 addition & 1 deletion transformer_engine/common/cast/nvfp4/specialized/quantize_transpose_nvfp4_tuned_1D.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@

#include "../../../common.h"
#include "../../../util/math.h"
#include "../../../util/ptx.cuh"
#include "../../../util/ptx_arch_spec.cuh"
#include "../../../utils.cuh"
#include "../core_nvfp4.cuh"

Expand Down
2 changes: 1 addition & 1 deletion transformer_engine/common/multi_tensor/compute_scale.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
#include <sstream>

#include "../recipe/recipe_common.cuh"
#include "../util/ptx.cuh"
#include "../util/ptx_arch_spec.cuh"
#include "../utils.cuh"
#include "multi_tensor_apply.cuh"

Expand Down
2 changes: 1 addition & 1 deletion transformer_engine/common/recipe/nvfp4.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#include <limits>

#include "../common.h"
#include "../util/ptx.cuh"
#include "../util/ptx_arch_spec.cuh"
#include "../utils.cuh"

namespace transformer_engine {
Expand Down
Loading
Loading