mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-14 18:02:52 +02:00
server: fix speculation after an image (#28715)
* server: fix speculation after an image Pass the actual position to the drafter after an image, instead of the token count. Affects every drafter, not just DFlash. * rename draft n_past to pos0 n_past is used to denote number of tokens and this parameter is meant to be a position
This commit is contained in:
@@ -188,7 +188,7 @@ int main(int argc, char ** argv) {
|
||||
common_speculative_get_draft_params(spec, seq_id) = {
|
||||
/* .drafting = */ true,
|
||||
/* .n_max = */ n_draft_max,
|
||||
/* .n_past = */ n_past,
|
||||
/* .pos0 = */ n_past,
|
||||
/* .id_last = */ id_last,
|
||||
/* .prompt = */ &prompt_tgt,
|
||||
/* .result = */ &draft, // output
|
||||
|
||||
Reference in New Issue
Block a user