ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-07 06:50:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge mainline llama.cpp (#3)

Browse Source 
* Merging mainline - WIP

* Merging mainline - WIP

AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.

* Merging mainline - fix Metal

* Remove check

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-07-27 07:55:01 +02:00
committed by GitHub
parent 0684c3e9c7
commit 154e0d75fc
612 changed files with 50817 additions and 165936 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
examples/perplexity/perplexity.cpp
View File

@@ -1991,6 +1991,12 @@ int main(int argc, char ** argv) {
params.n_batch = std::min(params.n_batch, n_kv);
} else {
params.n_batch = std::min(params.n_batch, params.n_ctx);
if (params.kl_divergence) {
params.n_parallel = 1;
} else {
// ensure there's at least enough seq_ids for HellaSwag
params.n_parallel = std::max(4, params.n_parallel);
}
}
if (params.ppl_stride > 0) {
@@ -2015,9 +2021,6 @@ int main(int argc, char ** argv) {
llama_model * model;
llama_context * ctx;
// ensure there's at least enough seq_ids for HellaSwag
params.n_parallel = std::max(4, params.n_parallel);
// load the model and apply lora adapter, if any
std::tie(model, ctx) = llama_init_from_gpt_params(params);
if (model == NULL) {