Skip to content

cuda: extended MMF_ROWS_PER_BLOCK #17051

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 2 commits into
base: master
Choose a base branch
from
+26 −11
Open

cuda: extended MMF_ROWS_PER_BLOCK #17051

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
afec3b4
extended MMF_ROWS_PER_BLOCK
Nov 6, 2025
c6c87bc
Merge branch 'ggml-org:master' into mmf_extended_tile
zhang-hui-yulo Nov 7, 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
37 changes: 26 additions & 11 deletions ggml/src/ggml-cuda/mmf.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -214,21 +214,30 @@ static __global__ void mul_mat_f(
return;
}

float sum = 0.0f;
static_assert(rows_per_block == warp_size, "need loop/check");
float sum[rows_per_block/warp_size] = {0.0f};
static_assert((rows_per_block % warp_size) == 0, "rows_per_block must be a multiple of warp_size.");
#pragma unroll
for (int i0 = 0; i0 < nwarps*rows_per_block; i0 += rows_per_block) {
const int i = i0 + threadIdx.x;
#pragma unroll
for (int i1 = 0; i1 < sizeof(sum)/sizeof(sum[0]); ++i1) {
const int i = i0 + i1*warp_size + threadIdx.x;

sum += buf_iw[j*kiw + i];
sum[i1] += buf_iw[j*kiw + i];
}
}

if constexpr (!has_ids) {
dst[j*stride_col_dst + row0 + threadIdx.x] = sum;
#pragma unroll
for (int i0 = 0; i0 < sizeof(sum)/sizeof(sum[0]); ++i0) {
dst[j*stride_col_dst + row0 + i0*warp_size + threadIdx.x] = sum[i0];
}
} else {
const int slot = (j < cols_per_block) ? slot_map[j] : -1;
if (slot >= 0 && (col_base + j) < ncols_dst_total) {
dst[slot*stride_channel_dst + j*stride_col_dst + row0 + threadIdx.x] = sum;
#pragma unroll
for (int i0 = 0; i0 < sizeof(sum)/sizeof(sum[0]); ++i0) {
dst[slot*stride_channel_dst + j*stride_col_dst + row0 + i0*warp_size + threadIdx.x] = sum[i0];
}
}
}
}
Expand Down Expand Up @@ -466,13 +475,16 @@ static __global__ void mul_mat_f_ids(
return;
}

float sum = 0.0f;
static_assert(rows_per_block == warp_size, "need loop/check");
float sum[rows_per_block/warp_size] = {0.0f};
static_assert((rows_per_block % warp_size) == 0, "rows_per_block must be a multiple of warp_size.");
#pragma unroll
for (int i0 = 0; i0 < nwarps*rows_per_block; i0 += rows_per_block) {
const int i = i0 + threadIdx.x;
#pragma unroll
for (int i1 = 0; i1 < sizeof(sum)/sizeof(sum[0]); ++i1) {
const int i = i0 + i1*warp_size + threadIdx.x;

sum += buf_iw[j*kiw + i];
sum[i1] += buf_iw[j * kiw + i];
}
}

const int global_j = col_base + j;
Expand All @@ -482,7 +494,10 @@ static __global__ void mul_mat_f_ids(
const int token = (int) qrm.x;
if (token < ncols_dst_total) {
const int slot = (int) qrm.y;
dst[slot*stride_channel_dst + token*stride_col_dst + row0 + threadIdx.x] = sum;
#pragma unroll
for (int i0 = 0; i0 < sizeof(sum)/sizeof(sum[0]); ++i0) {
dst[slot * stride_channel_dst + token * stride_col_dst + row0 + i0*warp_size + threadIdx.x] = sum[i0];
}
}
}
}
Expand Down