Skip to content

server : enable -td and -tbd parameters #15172

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

Jump to bottom
Merged
merged 2 commits into from
Aug 13, 2025
Merged

server : enable -td and -tbd parameters #15172

merged 2 commits into from
Aug 13, 2025

Conversation

CISC
Copy link
Collaborator

@CISC CISC commented Aug 8, 2025

These are useful to tweak performance.

Unless explicitly set they are inherited from regular parameters:

llama.cpp/common/arg.cpp

Lines 944 to 945 in cd6983d

postprocess_cpu_params(params.speculative.cpuparams, &params.cpuparams);
postprocess_cpu_params(params.speculative.cpuparams_batch, &params.cpuparams_batch);

@CISC CISC requested a review from ngxson as a code owner August 8, 2025 12:56
@CISC CISC merged commit b3e1666 into master Aug 13, 2025
51 checks passed
@CISC CISC deleted the cisc/server-draft-threads branch August 13, 2025 13:43
the-phobos pushed a commit to the-phobos/llama.cpp that referenced this pull request Aug 14, 2025
@CISC @the-phobos
server : enable -td and -tbd parameters (ggml-org#15172)
e691c19
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@ggerganov ggerganov ggerganov approved these changes

@ngxson ngxson ngxson approved these changes

Assignees

No one assigned

Labels

examples server

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@CISC @ggerganov @ngxson