CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: add unused vars to mmvf and mmvq (#16807)

Browse Source
This commit is contained in:
Aman Gupta
2025-10-28 10:31:21 +08:00
committed by GitHub
parent ad8d36beff
commit 463bbf20bf
2 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/mmvf.cu
View File

@@ -343,6 +343,10 @@ static __global__ void mul_mat_vec_f(
}
dst[tid*stride_col_dst + row] = value;
if constexpr (!has_fusion) {
GGML_UNUSED_VARS(use_gate, use_bias, use_gate_bias, glu_op, gate_x, x_bias, gate_bias, sumf_gate);
}
}
template<typename T, typename type_acc, int ncols_dst, int block_size>

4
ggml/src/ggml-cuda/mmvq.cu
View File

@@ -310,6 +310,10 @@ static __global__ void mul_mat_vec_q(
dst[j*stride_col_dst + threadIdx.x] = result;
}
}
if constexpr (!has_fusion) {
GGML_UNUSED_VARS(use_gate, use_bias, use_gate_bias, active_glu, gate_bias, x_bias, tmp_gate);
}
}
static std::pair<dim3, dim3> calc_launch_params(