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

Merge branch 'master' into xsn/private_batch_api

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-13 15:55:18 +01:00
parent 46596caf6d be7c303410
commit 17f954c8e2
173 changed files with 26425 additions and 16117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/embedding/embedding.cpp
View File

@ -4,6 +4,7 @@
#include "llama.h"
#include <ctime>
#include <algorithm>
#if defined(_MSC_VER)
#pragma warning(disable: 4244 4267) // possible loss of data
@ -37,7 +38,7 @@ static void batch_decode(llama_context * ctx, common_batch & batch, float * outp
const struct llama_model * model = llama_get_model(ctx);
// clear previous kv_cache values (irrelevant for embeddings)
llama_kv_cache_clear(ctx);
llama_kv_self_clear(ctx);
// run model
LOG_INF("%s: n_tokens = %d, n_seq = %d\n", __func__, llama_batch_ext_get_n_tokens(batch.get()), n_seq);