sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-14 21:14:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into HEAD

Browse Source
This commit is contained in:
Georgi Gerganov
2025-11-29 22:38:44 +02:00
parent 9028ebfea8 8c32d9d96d
commit d8d98bb4bb
98 changed files with 6675 additions and 1609 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/embedding/embedding.cpp
View File

@@ -104,12 +104,16 @@ int main(int argc, char ** argv) {
params.embedding = true;
// get max number of sequences per batch
const int n_seq_max = llama_max_parallel_sequences();
// if the number of prompts that would be encoded is known in advance, it's more efficient to specify the
// --parallel argument accordingly. for convenience, if not specified, we fallback to unified KV cache
// in order to support any number of prompts
if (params.n_parallel == 1) {
LOG_INF("%s: n_parallel == 1 -> unified KV cache is enabled\n", __func__);
params.kv_unified = true;
params.n_parallel = n_seq_max;
}
// utilize the full context
@@ -123,9 +127,6 @@ int main(int argc, char ** argv) {
params.n_ubatch = params.n_batch;
}
// get max number of sequences per batch
const int n_seq_max = llama_max_parallel_sequences();
llama_backend_init();
llama_numa_init(params.numa);