vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix index

Browse source
This commit is contained in:
Xuan Son Nguyen 2024-12-04 19:26:36 +01:00
parent ea1be7f8ac
commit 3b41ad53a3
1 changed files with 3 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/server/server.cpp
View file

@ -1169,6 +1169,7 @@ struct server_context {
void send_partial_response(server_slot & slot, completion_token_output tkn) {
server_task_result_cmpl_partial res;
res.id = slot.id_task;
res.index = slot.index;
res.n_decoded = slot.n_decoded;
res.n_prompt_tokens = slot.n_prompt_tokens;
res.content = tkn.text_to_send;
@ -1205,6 +1206,7 @@ struct server_context {
server_task_result_cmpl_final res;
res.id = slot.id_task;
res.id_slot = slot.id;
res.index = slot.index;
res.content = slot.generated_text;
res.n_decoded = slot.n_decoded;
@ -1411,7 +1413,7 @@ struct server_context {
|| result_raw->type == RESULT_TYPE_EMBD
|| result_raw->type == RESULT_TYPE_RERANK
) {
auto result = T::from_ptr(result_raw);
T result = T::from_ptr(result_raw);
const size_t idx = result.index;
GGML_ASSERT(idx < results.size() && "index out of range");
results[idx] = result;