tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 12:25:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix server

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-02-16 11:36:50 +01:00
parent 85ef80cbe9
commit aed4a8e980
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/server.cpp
View File

@ -3088,7 +3088,7 @@ struct server_context {
const bool need_embd = slot.task_type == SERVER_TASK_TYPE_EMBEDDING && llama_pooling_type(slot.ctx) == LLAMA_POOLING_TYPE_NONE; const bool need_embd = slot.task_type == SERVER_TASK_TYPE_EMBEDDING && llama_pooling_type(slot.ctx) == LLAMA_POOLING_TYPE_NONE;
std::array<llama_token, 1> seq_id = { slot.id }; std::array<llama_token, 1> seq_id = { slot.id };
llama_batch_ext_add_text_token(batch.get(), prompt_tokens[slot.n_past], slot.n_past, seq_id.data(), seq_id.size(), true); llama_batch_ext_add_text_token(batch.get(), prompt_tokens[slot.n_past], slot.n_past, seq_id.data(), seq_id.size(), need_embd);
if (slot.params.cache_prompt) { if (slot.params.cache_prompt) {
slot.cache_tokens.push_back(prompt_tokens[slot.n_past]); slot.cache_tokens.push_back(prompt_tokens[slot.n_past]);