tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

embeddings : fix batch sizes (#13076)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-04-24 22:29:22 +03:00
committed by GitHub
parent 87616f0680
commit 226251ed56
1 changed files with 7 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/embedding/embedding.cpp
View File

@ -89,6 +89,13 @@ int main(int argc, char ** argv) {
common_init(); common_init();
params.embedding = true; params.embedding = 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);
params.n_batch = params.n_ctx;
}
// For non-causal models, batch size must be equal to ubatch size // For non-causal models, batch size must be equal to ubatch size
params.n_ubatch = params.n_batch; params.n_ubatch = params.n_batch;
@ -134,7 +141,6 @@ int main(int argc, char ** argv) {
// max batch size // max batch size
const uint64_t n_batch = params.n_batch; const uint64_t n_batch = params.n_batch;
GGML_ASSERT(params.n_batch >= params.n_ctx);
// tokenize the prompts and trim // tokenize the prompts and trim
std::vector<std::vector<int32_t>> inputs; std::vector<std::vector<int32_t>> inputs;