Fix DeepSeek4HyperHead instantiation and usage in NNXDecoder - #4777
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request installs the Google Cloud CLI in the agent sidecar Dockerfile, increases retry attempts and sleep times for Gemini API calls, adds a mock failure log, and removes DeepSeek4 hyper-head logic from the NNX decoders. The review feedback highlights a duplicated comment line in nnx_decoders.py that was accidentally introduced during the refactoring.
| # After the final transformer layer, `y` holds the raw, un-normalized hidden state. | ||
| # After the final transformer layer, `y` holds the raw, un-normalized hidden state. |
There was a problem hiding this comment.
The comment explaining that y holds the raw, un-normalized hidden state is duplicated. Please remove the redundant line.
| # After the final transformer layer, `y` holds the raw, un-normalized hidden state. | |
| # After the final transformer layer, `y` holds the raw, un-normalized hidden state. | |
| # After the final transformer layer, y holds the raw, un-normalized hidden state. |
1 participant
Fix DeepSeek4HyperHead instantiation and usage in NNXDecoder