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

Stateless llama fixes #95

Merged
merged 1 commit into from
Oct 13, 2023
Merged

Stateless llama fixes #95

merged 1 commit into from
Oct 13, 2023

Conversation

dan-garvey
Copy link
Member

No description provided.

Adds support functions for debug-ability
@dan-garvey dan-garvey force-pushed the stateless_llama_fixes branch from 40e8d2e to a4bebf4 Compare October 12, 2023 04:10
@@ -281,8 +281,8 @@ def run_initialize(
token, *state = self.initialize(x, constraints=init_const)
updates = []
self.global_seq_step = IREE.tensor_dim(
state[0], 3
) # 3rd dimension of arbitrarily 0th kv tensor
state[0], 2
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh crap. Yeah. Good catch

@dan-garvey dan-garvey merged commit f3fc04b into main Oct 13, 2023
1 check passed
@dan-garvey dan-garvey deleted the stateless_llama_fixes branch October 13, 2023 05:17
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants