root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-30 13:24:35 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix assertion failure

Browse Source
This commit is contained in:
Jared Van Bortel 2024-01-10 13:44:34 -05:00
parent d5670d6e46
commit 8a99f69895
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
ggml-kompute.cpp
View File

@ -491,9 +491,11 @@ void ggml_vk_free_memory(ggml_vk_memory &memory)
static static
ggml_vk_memory * ggml_vk_find_tensor(struct ggml_kompute_context * ctx, struct ggml_tensor * t, uint64_t & offset) { ggml_vk_memory * ggml_vk_find_tensor(struct ggml_kompute_context * ctx, struct ggml_tensor * t, uint64_t & offset) {
ggml_backend_buffer_t buffer = t->view_src ? t->view_src->buffer : t->buffer;
// compatibility with ggml-backend // compatibility with ggml-backend
if (t->buffer && t->buffer->buft == ggml_backend_kompute_buffer_type()) { if (buffer && buffer->buft == ggml_backend_kompute_buffer_type()) {
ggml_vk_memory * buf_ctx = (ggml_vk_memory *) t->buffer->context; ggml_vk_memory * buf_ctx = (ggml_vk_memory *) buffer->context;
const intptr_t ioffs = reinterpret_cast<intptr_t>(t->data) - reinterpret_cast<intptr_t>(buf_ctx->data); const intptr_t ioffs = reinterpret_cast<intptr_t>(t->data) - reinterpret_cast<intptr_t>(buf_ctx->data);