ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 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
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
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,