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

ggml : change ggml_graph_compute() API to not require context (#1999)

Browse source 
* ggml_graph_compute: deprecate using ggml_context, try resolve issue #287

* rewrite: no longer consider backward compitability; plan and make_plan

* minor: rename ctx as plan; const

* remove ggml_graph_compute from tests/test-grad0.c, but current change breaks backward

* add static ggml_graph_compute_sugar()

* minor: update comments

* reusable buffers

* ggml : more consistent naming + metal fixes

* ggml : fix docs

* tests : disable grad / opt + minor naming changes

* ggml : add ggml_graph_compute_with_ctx()

- backwards compatible API
- deduplicates a lot of copy-paste

* ci : enable test-grad0

* examples : factor out plan allocation into a helper function

* llama : factor out plan stuff into a helper function

* ci : fix env

* llama : fix duplicate symbols + refactor example benchmark

* ggml : remove obsolete assert + refactor n_tasks section

* ggml : fix indentation in switch

* llama : avoid unnecessary bool

* ggml : remove comments from source file and match order in header

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Qingyou Meng 2023-07-08 00:24:01 +08:00 • committed by GitHub
parent 7242140283
commit 1d656d6360
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
13 changed files with 571 additions and 449 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/metal/metal.cpp
View file

@ -35,10 +35,9 @@ int main(int argc, char ** argv) {
struct ggml_context * ctx_eval = NULL;
struct ggml_cgraph gf = ggml_graph_import(fname_cgraph, &ctx_data, &ctx_eval);
gf.n_threads = 1;
// this allocates all Metal resources and memory buffers
auto * ctx_metal = ggml_metal_init();
auto * ctx_metal = ggml_metal_init(1);
const size_t max_size_data = ggml_get_max_tensor_size(ctx_data);
const size_t max_size_eval = ggml_get_max_tensor_size(ctx_eval);