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

Paged GPTBigCode Support #30

Merged
merged 9 commits into from
Jun 25, 2024
Merged

Paged GPTBigCode Support #30

merged 9 commits into from
Jun 25, 2024

Conversation

JRosenkranz
Copy link
Collaborator

  • Added support for PagedGPTBigCode
  • Updated inference script to handle multiple architectures
  • Moved PagedMultiHeadAttention to modules.attention

@JRosenkranz JRosenkranz requested review from nairbv and ani300 May 9, 2024 19:48
@JRosenkranz JRosenkranz self-assigned this May 9, 2024
@sahilsuneja1
Copy link
Contributor

@JRosenkranz Please merge #31 and #32 into paged_gpt_code branch first!

Update paged_gpt_bigcode.py
Update paged_speculative_inference.py
output = layer(
x=x,
mask=mask,
cache_data_layer=None
Copy link
Contributor

Choose a reason for hiding this comment

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

the value for the line should be assigned to a variable first or something, otherwise this looks like it says cache_data_layer=None

@sahilsuneja1
Copy link
Contributor

@JRosenkranz please merge #34 into paged_gpt_bigcode first :)

Update paged_llama.py for granite-3b-code
@JRosenkranz JRosenkranz merged commit 22f5132 into main Jun 25, 2024
3 checks passed
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.

3 participants