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

Fix paged attention for vision models on multiple devices #1071

Merged
merged 7 commits into from
Jan 18, 2025

Conversation

cdoko
Copy link
Collaborator

@cdoko cdoko commented Jan 18, 2025

The DeviceMapper was set to None for vision models before, now it's being passed properly. Tested working on Phi3V.

Copy link

Code Metrics Report
  ===============================================================================
 Language            Files        Lines         Code     Comments       Blanks
===============================================================================
 C Header                2           35           28            0            7
 Dockerfile              1           41           22           10            9
 JSON                   12          105          104            0            1
 Python                 66         2801         2425           72          304
 Shell                   1           57           22           18           17
 Plain Text              3         3723            0         2413         1310
 TOML                   18          619          550            2           67
 YAML                    2           21           19            2            0
-------------------------------------------------------------------------------
 Jupyter Notebooks       4            0            0            0            0
 |- Markdown             2           77           32           31           14
 |- Python               2          205          178            1           26
 (Total)                            282          210           32           40
-------------------------------------------------------------------------------
 Markdown               44         3491            0         2650          841
 |- BASH                 6          103          100            0            3
 |- JSON                 1           12           12            0            0
 |- Python               7          121          109            0           12
 |- Rust                13          440          373            0           67
 |- TOML                 2           75           63            0           12
 (Total)                           4242          657         2650          935
-------------------------------------------------------------------------------
 Rust                  301        96256        86291         1958         8007
 |- Markdown           145         1672           25         1524          123
 (Total)                          97928        86316         3482         8130
===============================================================================
 Total                 454       107149        89461         7125        10563
===============================================================================
  

Copy link
Owner

@EricLBuehler EricLBuehler left a comment

Choose a reason for hiding this comment

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

Thank you!

@EricLBuehler EricLBuehler merged commit cc24ad9 into master Jan 18, 2025
12 checks passed
@EricLBuehler EricLBuehler deleted the fix-vision-pa-multigpu branch January 18, 2025 10:35
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