Skip to content
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.

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

b3631 #309

Merged
merged 11 commits into from
Aug 27, 2024
Merged

b3631 #309

merged 11 commits into from
Aug 27, 2024

Conversation

Nexesenex
Copy link
Owner

No description provided.

JohannesGaessler and others added 11 commits August 25, 2024 22:11
This change fixes a bug where replacing text in a very long string could
cause llama.cpp to hang indefinitely. This is because the algorithm used
was quadratic, due to memmove() when s.replace() is called in a loop. It
seems most search results and LLM responses actually provide the O(n**2)
algorithm, which is a great tragedy. Using a builder string fixes things
* ggml : add ggml_ssm_conv metal impl

* ggml : add ssm_scan metal impl

ggml-ci
* metal : separate scale and mask from QKT in FA kernel

* metal : ne01 check no longer necessary

* metal : keep data in local memory
@Nexesenex Nexesenex merged commit 007428b into Nexesenex:skystream Aug 27, 2024
15 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants