tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-19 14:31:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

metal : handle buffers larger than device's maxBufferLength (#1826)

Browse Source 
* metal : handle buffers larger than device's maxBufferLength

* metal : print more verbose device info + handle errors

* metal : fix prints for overlapping views

* metal : minimize view overlap to try to utilize device memory better
This commit is contained in:
Georgi Gerganov
2023-06-18 09:09:47 +03:00
committed by GitHub
parent 57cd69460f
commit ce2c7d72e2
6 changed files with 125 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
ggml.h
View File

@@ -500,8 +500,9 @@ extern "C" {
GGML_API size_t ggml_set_scratch (struct ggml_context * ctx, struct ggml_scratch scratch);
GGML_API void ggml_set_no_alloc(struct ggml_context * ctx, bool no_alloc);
GGML_API void * ggml_get_mem_buffer(struct ggml_context * ctx);
GGML_API size_t ggml_get_mem_size (struct ggml_context * ctx);
GGML_API void * ggml_get_mem_buffer (const struct ggml_context * ctx);
GGML_API size_t ggml_get_mem_size (const struct ggml_context * ctx);
GGML_API size_t ggml_get_max_tensor_size(const struct ggml_context * ctx);
GGML_API struct ggml_tensor * ggml_new_tensor(
struct ggml_context * ctx,