Skip to content

spec - default MTP draft backend_sampling to off (#23903) #23921

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

Closed
ssam18 wants to merge 1 commit into from
+1 −1
Closed

spec - default MTP draft backend_sampling to off (#23903) #23921

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 1 addition & 1 deletion common/common.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -305,7 +305,7 @@ struct common_params_speculative_draft {
float p_split = 0.1f; // speculative decoding split probability
float p_min = 0.0f; // minimum speculative decoding probability (greedy)

bool backend_sampling = true; // offload draft sampling to the backend (default: on)
bool backend_sampling = false; // offload draft sampling to the backend (default: off; enabling has substantial per-sequence compute-buffer cost in MTP draft path that can OOM with --parallel N>1)

common_params_model mparams;

Expand Down