tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 20:45:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

context : add cache-less llama_context

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-02-20 15:18:45 +02:00
parent 072280ea6b
commit b1554be1d7
8 changed files with 1073 additions and 355 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/common.cpp
View File

@ -952,7 +952,7 @@ struct common_init_result common_init_from_params(common_params & params) {
}
if (params.ctx_shift && !llama_kv_self_can_shift(lctx)) {
LOG_WRN("%s: KV cache shifting is not supported for this model, disabling KV cache shifting\n", __func__);
LOG_WRN("%s: KV cache shifting is not supported for this context, disabling KV cache shifting\n", __func__);
params.ctx_shift = false;
}