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

llama : sync gguf-llama.cpp with latest llama.cpp (#2608)

Browse source 
* llama : sync gguf-llama.cpp with latest llama.cpp

* minor : indentation + assert

* llama : refactor gguf_buffer and gguf_ctx_buffer

* llama : minor
This commit is contained in:
Georgi Gerganov 2023-08-14 16:28:44 +03:00 • committed by GitHub
parent 6f64b6c0f8
commit f00780b2ee
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 692 additions and 463 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml-metal.h
View file

@ -38,6 +38,9 @@ struct ggml_metal_context;
struct ggml_metal_context * ggml_metal_init(int n_cb);
void ggml_metal_free(struct ggml_metal_context * ctx);
void * ggml_metal_host_malloc(size_t n);
void ggml_metal_host_free (void * data);
// set the number of command buffers to use
void ggml_metal_set_n_cb(struct ggml_metal_context * ctx, int n_cb);