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

metal : concurrently dispatch commands (#2358)

Browse source 
* metal: concurrently dispatch commands

Function `ggml_metal_graph_find_concurrency` will run and write
commands that can be issued concurrently to metal context `concur_list`
array, when `ggml_metal_graph_compute` is called for the first time.

* metal: don't call find_concurrency automatically.

* metal : code style changes

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Shouzheng Liu 2023-07-25 08:00:19 -04:00 • committed by GitHub
parent 9a08eaf3c4
commit 1aa18ef994
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 138 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

7
ggml-metal.h
View file

@ -61,6 +61,13 @@ 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);