Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
set b = ub when b > ub with embedding
  • Loading branch information
ahmedshakill committed Apr 14, 2025
commit 2741eee1abf9f805948fa546b68aec4bad8f173a
6 changes: 6 additions & 0 deletions examples/server/server.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -3002,6 +3002,12 @@ struct server_context {
}

if (slot.is_non_causal()) {
if (slot.task_type == SERVER_TASK_TYPE_EMBEDDING) {
if(n_batch > n_ubatch){
SRV_WRN("%s","setting batch= ubatch \n");
n_batch = n_ubatch;
}
}
if (slot.n_prompt_tokens > n_ubatch) {
slot.release();
send_error(slot, "input is too large to process. increase the physical batch size", ERROR_TYPE_SERVER);
Expand Down