Fix DeepSeek4HyperHead instantiation and usage in NNXDecoder - #4775
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. |
There was a problem hiding this comment.
Code Review
This pull request removes the DeepSeek4HyperHead initialization and usage from the NNX decoders when the MHC expansion rate is greater than one, simplifying the hidden state reduction logic. It also adds a mock failure log file. The review feedback points out a duplicated comment in nnx_decoders.py that should be cleaned up.
| # 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 duplicate comment.
| # 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. |
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
Fix DeepSeek4HyperHead instantiation and usage in NNXDecoder