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

examples : allow extracting embeddings from decoder contexts (#13797)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-05-26 14:03:54 +03:00
committed by GitHub
parent 22229314fc
commit 79c137f776
4 changed files with 10 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tools/server/server.cpp
View File

@ -3394,13 +3394,7 @@ struct server_context {
batch.logits + i,
};
int ret = 0;
if (do_encode) {
ret = llama_encode(ctx, batch_view);
} else {
ret = llama_decode(ctx, batch_view);
}
const int ret = llama_decode(ctx, batch_view);
metrics.on_decoded(slots);