ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

CUDA: backwards pass for misc. ops, add tests (#11257)

Browse source 
* CUDA: backwards pass for misc. ops, add tests

* remove restrict from pointers
This commit is contained in:
Johannes Gäßler 2025-01-16 16:43:38 +01:00 • committed by GitHub
parent 681149ced2
commit 9c8dcefe17
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
18 changed files with 930 additions and 332 deletions
Download patch file Download diff file Expand all files Collapse all files

38
ggml/src/ggml-cuda/out-prod.cu
View file

@ -11,16 +11,15 @@ void ggml_cuda_out_prod(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
GGML_ASSERT(src0->type == GGML_TYPE_F32);
GGML_ASSERT(src1->type == GGML_TYPE_F32);
GGML_ASSERT(dst->type == GGML_TYPE_F32);
GGML_ASSERT(ggml_is_contiguous(src0));
GGML_ASSERT(ggml_is_contiguous(dst));
GGML_ASSERT(ne01 == ne11);
GGML_ASSERT(ne0 == ne00);
GGML_ASSERT(ne1 == ne10);
GGML_ASSERT(ne2 == src0->ne[2]);
GGML_ASSERT(ne2 % src0->ne[2] == 0);
GGML_ASSERT(ne3 % src0->ne[3] == 0);
GGML_ASSERT(ne2 == src1->ne[2]);
GGML_ASSERT(ne3 == src0->ne[3]);
GGML_ASSERT(ne3 == src1->ne[3]);
const float * src0_d = (const float *) src0->data;
@ -33,8 +32,6 @@ void ggml_cuda_out_prod(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
const float alpha = 1.0f;
const float beta = 0.0f;
GGML_ASSERT(ne2 == 1);
GGML_ASSERT(ne3 == 1);
CUBLAS_CHECK(cublasSetStream(handle, stream));
const bool src1_T = ggml_is_transposed(src1);
@ -42,10 +39,27 @@ void ggml_cuda_out_prod(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
const int64_t ldb = (src1_T ? nb10 : nb11) / sizeof(float);
GGML_ASSERT( (src1_T ? nb11 : nb10) == sizeof(float));
CUBLAS_CHECK(
cublasSgemm(handle, CUBLAS_OP_N, src1_cublas_op,
ne0, ne1, ne01,
&alpha, src0_d, ne00,
src1_d, ldb,
&beta, dst_d, ne0));
// data strides in dimensions 2/3
const size_t s02 = nb02 / sizeof(float);
const size_t s03 = nb03 / sizeof(float);
const size_t s12 = nb12 / sizeof(float);
const size_t s13 = nb13 / sizeof(float);
const size_t s2 = nb2 / sizeof(float);
const size_t s3 = nb3 / sizeof(float);
// dps == dst per src0, used for group query attention
const int64_t dps2 = ne2 / ne02;
const int64_t dps3 = ne3 / ne03;
// TODO batched matrix multiplication
for (int64_t i3 = 0; i3 < ne3; ++i3) {
for (int64_t i2 = 0; i2 < ne2; ++i2) {
CUBLAS_CHECK(
cublasSgemm(handle, CUBLAS_OP_N, src1_cublas_op,
ne0, ne1, ne01,
&alpha, src0_d + (i3/dps3)*s03 + (i2/dps2)*s02, ne00,
src1_d + i3 *s13 + i2 *s12, ldb,
&beta, dst_d + i3 *s3 + i2 *s2, ne0));
}
}
}