Skip to content

llama : set n_outputs to 1 to avoid 0 outputs mean-pooling #15791

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
merged 3 commits into from
Sep 4, 2025
Merged

llama : set n_outputs to 1 to avoid 0 outputs mean-pooling #15791

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
af61b63
llama : set n_outputs to 1 to avoid 0 outputs mean-pooling
danbev Sep 4, 2025
4bf6181
add comment about not reserving graphs with zero outputs
danbev Sep 4, 2025
d3c0635
add assert in graph_reserve to ensure n_outputs >= 1
danbev Sep 4, 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
2 changes: 2 additions & 0 deletions src/llama-context.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -285,6 +285,8 @@ llama_context::llama_context(
const uint32_t n_seqs = cparams.kv_unified ? 1 : cparams.n_seq_max;
const uint32_t n_tokens = std::min(cparams.n_ctx, cparams.n_ubatch);

n_outputs = 1;

LLAMA_LOG_DEBUG("%s: worst-case: n_tokens = %d, n_seqs = %d, n_outputs = %d\n", __func__, n_tokens, n_seqs, n_outputs);

// resolve automatic Flash Attention use
Expand Down
Loading