tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-02 05:15:47 +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

2
examples/lookup/lookup.cpp
View File

@ -194,7 +194,7 @@ int main(int argc, char ** argv){
// KV cache management
// clean the cache of draft tokens that weren't accepted
llama_kv_cache_seq_rm(ctx, 0, n_past, -1);
llama_kv_self_seq_rm(ctx, 0, n_past, -1);
const llama_seq_id seq_id = 0;
llama_batch_ext_clear(batch_tgt);