Skip to content

opt(ggml): No need to allocate memory for ggml_new_tensor_impl for mmaped case #916

New issue

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

#

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

Already on GitHub? # to your account

Jump to bottom
Closed
jon-chuang opened this issue Apr 12, 2023 · 1 comment
Closed

opt(ggml): No need to allocate memory for ggml_new_tensor_impl for mmaped case #916

jon-chuang opened this issue Apr 12, 2023 · 1 comment

Comments

@jon-chuang
Copy link
Contributor

The solution is simple. As per llama.cpp (https://github.com/ggerganov/llama.cpp/blob/f76cb3a34d6a6b03afb96650e39495f201eac042/llama.cpp#L933), set ctx.no_alloc to true.
@jon-chuang
Copy link
Contributor Author

Oops, wrong repo

@Bearsaerker Bearsaerker mentioned this issue Mar 12, 2025
Open
# for free to join this conversation on GitHub. Already have an account? # to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@jon-chuang