Uh oh!
There was an error while loading. Please reload this page.
Fix static_llama to read some previously hardcoded options from ModelArgs - #8846
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8846
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 53f000f with merge base 781b082 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
…Args Differential Revision: D70414663
facebook-github-bot
commented
Feb 28, 2025
This pull request was exported from Phabricator. Differential Revision: D70414663 |
facebook-github-bot
commented
Feb 28, 2025
This pull request was exported from Phabricator. Differential Revision: D70414663 |
| self.dim = config.dim | ||
| self.n_heads = config.n_heads | ||
| self.head_dim = config.dim // config.n_heads | ||
| self.head_dim = config.head_dim |
There was a problem hiding this comment.
Maybe I miss something, isn't head_dim the same as dim / n_heads?
There was a problem hiding this comment.
Not necessarily, it can be anything, it's internal to the attention, the wo layer make sure the output of the attention has size dim.
Summary: After pytorch#8846, the models exported correctly, but failed to run on-device with segmentation error. This diff fixes that error. Reviewed By: sxu, billmguo Differential Revision: D70538475
Summary: After pytorch#8846, the models exported correctly, but failed to run on-device with segmentation error. This diff fixes that error. Reviewed By: sxu, billmguo Differential Revision: D70538475
Differential Revision: D70414663