Skip to content

CUDA: Remove unneded bias/gate dims in fused mmvq #16858

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 3 commits into from
Nov 1, 2025
Merged

CUDA: Remove unneded bias/gate dims in fused mmvq #16858

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
44987f7
CUDA: Remove unneded bias/gate dims in fused mmvq
ORippler Oct 30, 2025
af6465a
Apply suggestions from code review
ORippler Oct 30, 2025
f79bd92
Fix "Error 991-D: extra braces are nonstandard" during compilation
ORippler Oct 31, 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
12 changes: 6 additions & 6 deletions ggml/src/ggml-cuda/mmvq.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -190,8 +190,8 @@ static __global__ void mul_mat_vec_q(

const uint32_t channel_bias = ids ? channel_x : channel_dst;

float x_biases[ncols_dst][rows_per_cuda_block] = { { 0.0f } };
float gate_biases[ncols_dst][rows_per_cuda_block] = { { 0.0f } };
float x_biases[ncols_dst] = { { 0.0f } };
float gate_biases[ncols_dst] = { { 0.0f } };
if constexpr (has_fusion) {
if (use_bias) {
x_bias = x_bias + sample_dst*stride_sample_dst + channel_bias*stride_channel_dst + row0;
Expand All @@ -200,7 +200,7 @@ static __global__ void mul_mat_vec_q(
if (threadIdx.x < rows_per_cuda_block && threadIdx.y == 0 &&
(rows_per_cuda_block == 1 || uint32_t(row0 + threadIdx.x) < stride_col_dst)) {
for (int j = 0; j < ncols_dst; ++j) {
x_biases[j][threadIdx.x] = x_bias[j * stride_col_dst + threadIdx.x];
x_biases[j] = x_bias[j * stride_col_dst + threadIdx.x];
}
}
}
Expand All @@ -209,7 +209,7 @@ static __global__ void mul_mat_vec_q(
if (threadIdx.x < rows_per_cuda_block && threadIdx.y == 0 &&
(rows_per_cuda_block == 1 || uint32_t(row0 + threadIdx.x) < stride_col_dst)) {
for (int j = 0; j < ncols_dst; ++j) {
gate_biases[j][threadIdx.x] = gate_bias[j * stride_col_dst + threadIdx.x];
gate_biases[j] = gate_bias[j * stride_col_dst + threadIdx.x];
}
}
}
Expand Down Expand Up @@ -299,12 +299,12 @@ static __global__ void mul_mat_vec_q(
float result = tmp[j][threadIdx.x];
if constexpr (has_fusion) {
if (use_bias) {
result += x_biases[j][threadIdx.x];
result += x_biases[j];
}
if (use_gate) {
float gate_value = tmp_gate[j][threadIdx.x];
if (use_gate_bias) {
gate_value += gate_biases[j][threadIdx.x];
gate_value += gate_biases[j];
}
switch (active_glu) {
case GGML_GLU_OP_SWIGLU:
Expand Down
Loading