tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 20:25:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : remove old commented code [no ci]

Browse Source
This commit is contained in:
Georgi Gerganov
2025-03-20 18:19:55 +02:00
parent 8a23b4a54a
commit b8b173274d
1 changed files with 0 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/server/server.cpp
View File

@ -3081,7 +3081,6 @@ struct server_context {
// without pooling, we want to output the embeddings for all the tokens in the batch // without pooling, we want to output the embeddings for all the tokens in the batch
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;
//batch.add_text(prompt_tokens[slot.n_past], slot.n_past, slot.id, need_embd);
llama_batch_ext_add_text(batch.get(), prompt_tokens[slot.n_past], slot.n_past, &slot.id, 1, need_embd); llama_batch_ext_add_text(batch.get(), prompt_tokens[slot.n_past], slot.n_past, &slot.id, 1, need_embd);
if (slot.params.cache_prompt) { if (slot.params.cache_prompt) {
@ -3109,7 +3108,6 @@ struct server_context {
} }
// extract the logits only for the last token // extract the logits only for the last token
//batch.set_logits_last();
llama_batch_ext_set_output_last(batch.get()); llama_batch_ext_set_output_last(batch.get());
slot.n_decoded = 0; slot.n_decoded = 0;
@ -3280,13 +3278,10 @@ struct server_context {
} }
// construct the speculation batch // construct the speculation batch
//slot.batch_spec.clear();
//slot.batch_spec.add_text(id, slot.n_past, slot.id, true);
llama_batch_ext_clear(slot.batch_spec.get()); llama_batch_ext_clear(slot.batch_spec.get());
llama_batch_ext_add_text(slot.batch_spec.get(), id, slot.n_past, &slot.id, 1, true); llama_batch_ext_add_text(slot.batch_spec.get(), id, slot.n_past, &slot.id, 1, true);
for (size_t i = 0; i < draft.size(); ++i) { for (size_t i = 0; i < draft.size(); ++i) {
//slot.batch_spec.add_text(draft[i], slot.n_past + 1 + i, slot.id, true);
llama_batch_ext_add_text(slot.batch_spec.get(), draft[i], slot.n_past + 1 + i, &slot.id, 1, true); llama_batch_ext_add_text(slot.batch_spec.get(), draft[i], slot.n_past + 1 + i, &slot.id, 1, true);
} }