matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-11 16:26:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

update llama.cpp

Browse Source
This commit is contained in:
Michael Yang
2023-07-25 10:49:30 -07:00
parent 688661ab9b
commit 18ffeeec45
16 changed files with 2607 additions and 1567 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
llama/ggml-metal.h
View File

@@ -1,7 +1,7 @@
//go:build darwin
/**
* llama.cpp - git e782c9e735f93ab4767ffc37462c523b73a17ddc
* llama.cpp - git 7c529cede6e84054e77a3eceab31c53de7b2f55b
*
* MIT License
*
@@ -89,6 +89,13 @@ void ggml_metal_set_tensor(struct ggml_metal_context * ctx, struct ggml_tensor *
// get data from the device into host memory
void ggml_metal_get_tensor(struct ggml_metal_context * ctx, struct ggml_tensor * t);
// try to find operations that can be run concurrently in the graph
// you should run it again if the topology of your graph changes
void ggml_metal_graph_find_concurrency(struct ggml_metal_context * ctx, struct ggml_cgraph * gf);
// if the graph has been optimized for concurrently dispatch
bool ggml_metal_if_optimized(struct ggml_metal_context * ctx);
// same as ggml_graph_compute but uses Metal
// creates gf->n_threads command buffers in parallel
void ggml_metal_graph_compute(struct ggml_metal_context * ctx, struct ggml_cgraph * gf);