tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-13 03:47:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

tests : update for LLAMA_SET_ROWS=1 (#14961)

Browse Source 
* test-thread-safety : each context uses a single sequence

* embedding : handle --parallel argument

ggml-ci

* save-load : handle -np 1

ggml-ci

* thread-safety : avoid overriding threads, reduce test case arg

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-30 15:12:02 +03:00
committed by GitHub
parent 1e15bfd42c
commit 00131d6eaf
5 changed files with 19 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/embedding/embedding.cpp
View File

@@ -81,6 +81,14 @@ int main(int argc, char ** argv) {
params.embedding = true;
// 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;
}
// utilize the full context
if (params.n_batch < params.n_ctx) {
LOG_WRN("%s: setting batch size to %d\n", __func__, params.n_ctx);

6
examples/save-load-state/save-load-state.cpp
View File

@@ -15,6 +15,12 @@ int main(int argc, char ** argv) {
return 1;
}
if (params.n_parallel == 1) {
// the example uses 2 sequences, so when n_parallel == 1, we need to enable unified kv cache
printf("%s: n_parallel == 1, enabling unified kv cache\n", __func__);
params.kv_unified = true;
}
common_init();
if (params.n_predict < 0) {