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

speculative : refactor and add a simpler example (#10362)

Browse source 
* speculative : refactor and add a simpler example

ggml-ci

* speculative : clean-up and add comments and TODOs [no ci]

* speculative : manage context in common_speculative

ggml-ci

* speculative : simplify

ggml-ci

* speculative : simplify (cont)

ggml-ci

* speculative : add --draft-min CLI arg

* speculative : minor fixup

* make : build fixes

* speculative : do not redraft previous drafts

ggml-ci

* speculative : fix the draft sampling

ggml-ci

* speculative : fix compile warning

* common : refactor args

ggml-ci

* common : change defaults [no ci]

* common : final touches

ggml-ci
This commit is contained in:
Georgi Gerganov 2024-11-25 09:58:41 +02:00 • committed by GitHub
parent cce5a90075
commit d9d54e498d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
28 changed files with 1028 additions and 326 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/llava/llava-cli.cpp
View file

@ -191,7 +191,7 @@ static void process_prompt(struct llava_context * ctx_llava, struct llava_image_
LOG("\n");
struct common_sampler * smpl = common_sampler_init(ctx_llava->model, params->sparams);
struct common_sampler * smpl = common_sampler_init(ctx_llava->model, params->sampling);
if (!smpl) {
LOG_ERR("%s: failed to initialize sampling subsystem\n", __func__);
exit(1);

2
examples/llava/minicpmv-cli.cpp
View file

@ -237,7 +237,7 @@ static struct common_sampler * llama_init(struct llava_context * ctx_llava, comm
LOG_INF("\n");
struct common_sampler * smpl = common_sampler_init(ctx_llava->model, params->sparams);
struct common_sampler * smpl = common_sampler_init(ctx_llava->model, params->sampling);
return smpl;
}