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

llama : more consistent names of count variables (#5994)

Browse source 
* llama : more consistent names of count variables

ggml-ci

* llama : n_parallel -> n_seq_max

* common : fix param name

* examples : fix param name
This commit is contained in:
Georgi Gerganov 2024-03-11 17:49:47 +02:00 • committed by GitHub
parent 83796e62bc
commit 05b06210c9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 35 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/batched/batched.cpp
View file

@ -80,7 +80,7 @@ int main(int argc, char ** argv) {
ctx_params.seed = 1234;
ctx_params.n_ctx = n_kv_req;
ctx_params.n_batch = std::max(n_len, n_parallel);
ctx_params.n_parallel = n_parallel;
ctx_params.n_seq_max = n_parallel;
ctx_params.n_threads = params.n_threads;
ctx_params.n_threads_batch = params.n_threads_batch == -1 ? params.n_threads : params.n_threads_batch;