Skip to content

musa: remove nrows_x in mul_mat_q_process_tile #13325

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

Merged
merged 1 commit into from
May 7, 2025
Merged

musa: remove nrows_x in mul_mat_q_process_tile #13325

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 4 additions & 4 deletions ggml/src/ggml-cuda/mmq.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2522,7 +2522,7 @@ template <ggml_type type, int mmq_x, int nwarps, bool need_check, bool fixup>
static __device__ __forceinline__ void mul_mat_q_process_tile(
const char * __restrict__ x, const int offset_x, const int * __restrict__ y,
const int * __restrict__ ids_dst, float * __restrict__ dst, float * __restrict__ tmp_fixup,
const int nrows_x, const int stride_row_x, const int ncols_y, const int stride_col_dst,
const int stride_row_x, const int ncols_y, const int stride_col_dst,
const int tile_x_max_i, const int tile_y_max_j, const int kb0_start, const int kb0_stop) {

constexpr int qk = ggml_cuda_type_traits<type>::qk;
Expand Down Expand Up @@ -2689,7 +2689,7 @@ static __global__ void mul_mat_q(

constexpr bool fixup = false;
mul_mat_q_process_tile<type, mmq_x, nwarps, need_check, fixup>
(x, offset_x, y + offset_y, ids_dst_shared, dst + offset_dst, tmp_fixup, nrows_x, stride_row_x, ncols_y, stride_col_dst,
(x, offset_x, y + offset_y, ids_dst_shared, dst + offset_dst, tmp_fixup, stride_row_x, ncols_y, stride_col_dst,
tile_x_max_i, tile_y_max_j, 0, ncols_x/qk);
return;
}
Expand Down Expand Up @@ -2767,7 +2767,7 @@ static __global__ void mul_mat_q(

constexpr bool fixup = false; // All but (potentially) the last iterations write their data to dst rather than the fixup buffer.
mul_mat_q_process_tile<type, mmq_x, nwarps, need_check, fixup>
(x, offset_x, y + offset_y, ids_dst_shared, dst + offset_dst, tmp_fixup, nrows_x, stride_row_x, ncols_y, stride_col_dst,
(x, offset_x, y + offset_y, ids_dst_shared, dst + offset_dst, tmp_fixup, stride_row_x, ncols_y, stride_col_dst,
tile_x_max_i, tile_y_max_j, kb0_start, kb0_stop);

kbc += blocks_per_ne00;
Expand Down Expand Up @@ -2834,7 +2834,7 @@ static __global__ void mul_mat_q(

constexpr bool fixup = true; // Last index writes its data to fixup buffer to avoid data races with other blocks.
mul_mat_q_process_tile<type, mmq_x, nwarps, need_check, fixup>
(x, offset_x, y + offset_y, ids_dst_shared, dst + offset_dst, tmp_fixup, nrows_x, stride_row_x, ncols_y, stride_col_dst,
(x, offset_x, y + offset_y, ids_dst_shared, dst + offset_dst, tmp_fixup, stride_row_x, ncols_y, stride_col_dst,
tile_x_max_i, tile_y_max_j, kb0_start, kb0_stop);
}

Expand Down
Loading