Skip to content

[Common] Remove nv-internal-* comments #3280

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
ksivaman wants to merge 2 commits into
base: main
Choose a base branch
from
+6 −6
Open

[Common] Remove nv-internal-* comments #3280

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7d683f5
remove nv-internal comments
ksivaman Jul 29, 2026
f148fcf
Merge branch 'main' into rm_nv_internal_comments
ksivaman Jul 29, 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
4 changes: 2 additions & 2 deletions ...common/hadamard_transform/graph_safe_group_row_cast_col_hadamard_transform_cast_fusion.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -746,7 +746,7 @@ __launch_bounds__(512, 1) __global__ static void group_row_col_rht_gemm_device_g

cutlass::arch::NamedBarrier::sync(NumEpilogueColQuantThreadCount,
cutlass::arch::ReservedNamedBarriers::EpilogueBarrier);
// Aligning with TensorEngine's recipe to generate scale factors // {$nv-internal-release}
// Aligning with TensorEngine's recipe to generate scale factors
static constexpr float fp4_max = 6.0f;
static constexpr float fp8_max = 448.0f;
static constexpr float fp4_max_inv = 1.0f / fp4_max;
Expand Down Expand Up @@ -1003,7 +1003,7 @@ __launch_bounds__(512, 1) __global__ static void group_row_col_rht_gemm_device_g
shape_rep, num_tensors, (scheduler.tile_n_base() * size<1>(epilogue_tiler)) * M,
packed_N, M, offsets);
float a_global_amax_val = shared_storage.global_a_amax[group_idx];
// Aligning with TensorEngine's recipe to generate scale factors // {$nv-internal-release}
// Aligning with TensorEngine's recipe to generate scale factors
static constexpr float fp4_max = 6.0f;
static constexpr float fp8_max = 448.0f;
static constexpr float fp4_max_inv = 1.0f / fp4_max;
Expand Down
4 changes: 2 additions & 2 deletions ...mer_engine/common/hadamard_transform/group_row_cast_col_hadamard_transform_cast_fusion.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -728,7 +728,7 @@ __launch_bounds__(512, 1) __global__ static void group_row_col_rht_gemm_device(

cutlass::arch::NamedBarrier::sync(NumEpilogueColQuantThreadCount,
cutlass::arch::ReservedNamedBarriers::EpilogueBarrier);
// Aligning with TensorEngine's recipe to generate scale factors // {$nv-internal-release}
// Aligning with TensorEngine's recipe to generate scale factors
static constexpr float fp4_max = 6.0f;
static constexpr float fp8_max = 448.0f;
static constexpr float fp4_max_inv = 1.0f / fp4_max;
Expand Down Expand Up @@ -980,7 +980,7 @@ __launch_bounds__(512, 1) __global__ static void group_row_col_rht_gemm_device(

int group_idx = GetGroupIdx(&args, scheduler.tile_n_base() * size<1>(epilogue_tiler));
float a_global_amax_val = shared_storage.global_a_amax[group_idx];
// Aligning with TensorEngine's recipe to generate scale factors // {$nv-internal-release}
// Aligning with TensorEngine's recipe to generate scale factors
static constexpr float fp4_max = 6.0f;
static constexpr float fp8_max = 448.0f;
static constexpr float fp4_max_inv = 1.0f / fp4_max;
Expand Down
4 changes: 2 additions & 2 deletions transformer_engine/common/hadamard_transform/row_cast_col_hadamard_transform_cast_fusion.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -709,7 +709,7 @@ __global__ static void row_col_rht_gemm_device(
auto thr_t2r = tiled_t2r.get_slice(local_thread_idx);
auto thr_r2g = tiled_r2g.get_slice(local_thread_idx);

// Aligning with TensorEngine's recipe to generate scale factors // {$nv-internal-release}
// Aligning with TensorEngine's recipe to generate scale factors
static constexpr float fp4_max = 6.0f;
static constexpr float fp8_max = 448.0f;
float const fp4_max_inv = 1.0f / fp4_max;
Expand Down Expand Up @@ -905,7 +905,7 @@ __global__ static void row_col_rht_gemm_device(
cute::Tensor tQArSFA = make_tensor_like(tQAgSFA(_, _, _, _0{}, _0{}));
cute::Tensor tQApSFA = thr_s2r.partition_D(pSFA_mn);

// Aligning with TensorEngine's recipe to generate scale factors // {$nv-internal-release}
// Aligning with TensorEngine's recipe to generate scale factors
static constexpr float fp4_max = 6.0f;
static constexpr float fp8_max = 448.0f;
float const fp4_max_inv = 1.0f / fp4_max;
Expand Down
Loading