mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-26 03:14:35 +00:00
[SYCL] Re-enabled mul_mat_batched_sycl (#8095)
This commit is contained in:
parent
2df373ac40
commit
083bacce14
@ -4620,7 +4620,7 @@ static void ggml_sycl_mul_mat(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||||||
} else if (!split && src0->type == GGML_TYPE_F16 && !ggml_is_contiguous(src0) && !ggml_is_transposed(src1) && src1->ne[1] == 1) {
|
} else if (!split && src0->type == GGML_TYPE_F16 && !ggml_is_contiguous(src0) && !ggml_is_transposed(src1) && src1->ne[1] == 1) {
|
||||||
// KQV single-batch
|
// KQV single-batch
|
||||||
ggml_sycl_mul_mat_vec_nc(ctx, src0, src1, dst);
|
ggml_sycl_mul_mat_vec_nc(ctx, src0, src1, dst);
|
||||||
} else if (!split && src0->type == GGML_TYPE_F16 && (src1->type == GGML_TYPE_F16) && !ggml_is_transposed(src0) && !ggml_is_transposed(src1) && src1->ne[2]*src1->ne[3] > 1) {
|
} else if (!split && src0->type == GGML_TYPE_F16 && !ggml_is_transposed(src0) && !ggml_is_transposed(src1) && src1->ne[2]*src1->ne[3] > 1) {
|
||||||
// KQ + KQV multi-batch
|
// KQ + KQV multi-batch
|
||||||
ggml_sycl_mul_mat_batched_sycl(ctx, src0, src1, dst);
|
ggml_sycl_mul_mat_batched_sycl(ctx, src0, src1, dst);
|
||||||
} else if (use_dequantize_mul_mat_vec) {
|
} else if (use_dequantize_mul_mat_vec) {
|
||||||
|
Loading…
Reference in New Issue
Block a user