Skip to content

LLM inference in C/C++

C++ ggml

ggml-cuda: Allow transpose-free gemmv computation (#26171)

Robert Esclapeze1a1abb78746
diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
index d22b5657d9..3e2c622951 100644
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda/ggml-cuda.cu
@@ -1836,6 +1836,20 @@ static void ggml_cuda_mul_mat(ggml_backend_cuda_context & ctx, const ggml_tensor
ggml_cuda_mul_mat_vec_f(ctx, src0, src1, nullptr, dst);
return;
}
+ // A transposed vector can still use MMVQ (i.e. ne01 == 1)
+ if (ne01 == 1 && ne11 > MMVF_MAX_BATCH_SIZE && ne2 == 1 && ne3 == 1
+ && src0->type == GGML_TYPE_F32
+ && ggml_is_contiguous(src0) && ggml_is_contiguous(src1) && ggml_is_contiguous(dst)
+ && ggml_cuda_should_use_mmvf(src1->type, cc, src1->ne, src1->nb, /*ne11 =*/ 1)) {
+ ggml_tensor dst_vec = *dst;
+ dst_vec.ne[0] = ne11;
+ dst_vec.ne[1] = 1;
+ dst_vec.nb[1] = dst_vec.nb[0]*ne11;
+ dst_vec.nb[2] = dst_vec.nb[1];
+ dst_vec.nb[3] = dst_vec.nb[1];
+ ggml_cuda_mul_mat_vec_f(ctx, src1, src0, nullptr, &dst_vec);
+ return;
+ }
if (ggml_cuda_should_use_mmf(src0->type, cc, warp_size, src0->ne, src0->nb, ne11, /*mul_mat_id =*/ false)) {
ggml_cuda_mul_mat_f(ctx, src0, src1, nullptr, dst);
return;
diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp
index ef18ecef8a..e8d0e00d5b 100644
--- a/tests/test-backend-ops.cpp
+++ b/tests/test-backend-ops.cpp
@@ -8838,6 +8838,10 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_mul_mat(GGML_TYPE_Q8_0, GGML_TYPE_F32, 2880, 32, 2880, {1, 1}, {1, 1}));
test_cases.emplace_back(new test_mul_mat(GGML_TYPE_MXFP4, GGML_TYPE_F32, 2880, 32, 2880, {1, 1}, {1, 1}));
+ // m == 1, with n on both sides of MMVF_MAX_BATCH_SIZE (8): mmvf below, operand swap above
+ for (int64_t n : {1, 7, 8, 9, 16, 128, 512}) {
+ test_cases.emplace_back(new test_mul_mat(GGML_TYPE_F32, GGML_TYPE_F32, 1, n, 2048, {1, 1}, {1, 1}));
+ }
#if 0
{