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

Fix MUL_MAT_ID matrix vector shader dispatch size

Browse source
This commit is contained in:
0cc4m 2024-05-29 23:38:07 +02:00
parent 8ecdda1e5e
commit c8f93774c9
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml-vulkan.cpp
View file

@ -3731,7 +3731,7 @@ static void ggml_vk_mul_mat_vec_id_q_f16(ggml_backend_vk_context * ctx, vk_conte
ggml_vk_sync_buffers(subctx); ggml_vk_sync_buffers(subctx);
ggml_vk_dispatch_pipeline(ctx, subctx, dmmv, ggml_vk_dispatch_pipeline(ctx, subctx, dmmv,
{ { d_X, x_buf_offset, x_sz * ne02 * ne03 }, { d_Y, y_buf_offset, y_sz * ne12 * ne13 }, { d_D, d_buf_offset, d_sz * ne22 * ne23}, { d_ids, ids_buf_offset, ids_sz } }, { { d_X, x_buf_offset, x_sz * ne02 * ne03 }, { d_Y, y_buf_offset, y_sz * ne12 * ne13 }, { d_D, d_buf_offset, d_sz * ne22 * ne23}, { d_ids, ids_buf_offset, ids_sz } },
sizeof(vk_mat_vec_id_push_constants), &pc, { (uint32_t)ne01, (uint32_t)(ne12 * ne13), (uint32_t)nei0 }); sizeof(vk_mat_vec_id_push_constants), &pc, { (uint32_t)ne01, (uint32_t)(ne22 * ne23), 1 });
} }
static void ggml_vk_mul_mat_id(ggml_backend_vk_context * ctx, vk_context * subctx, const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * src2, ggml_tensor * dst) { static void ggml_vk_mul_mat_id(ggml_backend_vk_context * ctx, vk_context * subctx, const ggml_tensor * src0, const ggml_tensor * src1, const ggml_tensor * src2, ggml_tensor * dst) {