Skip to content

Disable KV cache shifting automatically for unsupported models #11053

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ggerganov merged 2 commits into from
Jan 3, 2025
+2 −3
Merged

Disable KV cache shifting automatically for unsupported models #11053

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
672983a
Disable KV cache shifting automatically for unsupported models
MollySophia Jan 3, 2025
9c529a7
Update common/common.cpp
MollySophia Jan 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions common/common.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -889,9 +889,8 @@ struct common_init_result common_init_from_params(common_params & params) {
}

if (params.ctx_shift && !llama_kv_cache_can_shift(lctx)) {
LOG_ERR("%s: KV cache shifting is not supported for this model (--no-context-shift to disable)'\n", __func__);
llama_free_model(model);
return iparams;
LOG_WRN("%s: KV cache shifting is not supported for this model, disabling KV cache shifting'\n", __func__);
Comment thread
MollySophia marked this conversation as resolved.
Outdated
params.ctx_shift = false;
}

if (!params.control_vectors.empty()) {
Expand Down