-
Notifications
You must be signed in to change notification settings - Fork 749
Create a forked KV IO transformer for exporting coreML Llama #7778
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
base: main
Are you sure you want to change the base?
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7778
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New FailuresAs of commit b90b99e with merge base 948fba6 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
This pull request was exported from Phabricator. Differential Revision: D68424012 |
|
@pytorchbot label "topic: not user facing" |
…#7778) Summary: Create a forked KV IO transformer for exporting coreML Llama - As discussed in the group chat " Design: KV cache IO on ANE: llama_transformer vs. static_llama", we agreed that forking a KV IO version llama_transformer is best for code quality and coreML/ANE development purposes Differential Revision: D68424012
81aa7d3 to
d9e61ad
Compare
|
This pull request was exported from Phabricator. Differential Revision: D68424012 |
…#7778) Summary: Create a forked KV IO transformer for exporting coreML Llama - As discussed in the group chat "Design: KV cache IO on ANE: llama_transformer vs. static_llama", we agreed that forking a KV IO version llama_transformer is best for code quality and coreML/ANE development purposes Differential Revision: D68424012
d9e61ad to
b90b99e
Compare
|
This pull request was exported from Phabricator. Differential Revision: D68424012 |
|
Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as |
|
Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as |
Summary:
Create a forked KV IO transformer for exporting coreML Llama
Design: KV cache IO on ANE: llama_transformer vs. static_llama", we agreed that forking a KV IO version llama_transformer is best for code quality and coreML/ANE development purposes
Differential Revision: D68424012