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

8
examples/save-load-state/save-load-state.cpp
View file

@ -9,7 +9,7 @@ int main(int argc, char ** argv) {
common_params params;
params.prompt = "The quick brown fox";
params.sparams.seed = 1234;
params.sampling.seed = 1234;
if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_COMMON)) {
return 1;
@ -42,7 +42,7 @@ int main(int argc, char ** argv) {
llama_sampler * smpl = llama_sampler_chain_init(sparams);
llama_sampler_chain_add(smpl, llama_sampler_init_dist(params.sparams.seed));
llama_sampler_chain_add(smpl, llama_sampler_init_dist(params.sampling.seed));
// tokenize prompt
auto tokens = common_tokenize(ctx, params.prompt, true);
@ -106,7 +106,7 @@ int main(int argc, char ** argv) {
llama_sampler * smpl2 = llama_sampler_chain_init(sparams);
llama_sampler_chain_add(smpl2, llama_sampler_init_dist(params.sparams.seed));
llama_sampler_chain_add(smpl2, llama_sampler_init_dist(params.sampling.seed));
printf("\nsecond run: %s", params.prompt.c_str());
@ -169,7 +169,7 @@ int main(int argc, char ** argv) {
llama_sampler * smpl3 = llama_sampler_chain_init(sparams);
llama_sampler_chain_add(smpl3, llama_sampler_init_dist(params.sparams.seed));
llama_sampler_chain_add(smpl3, llama_sampler_init_dist(params.sampling.seed));
printf("\nsingle seq run: %s", params.prompt.c_str());