Closed
Conversation
… and kernels. - Adapt tensors, task graphs, and layer planners to support `HalfFloatArray`. - Replace FP32 arrays with FP16-compatible implementations in key inference states (`wrapX`). - Add new FP16-specific kernels for data transfer and activation computations. - Optimize Q8_0 quantized operations with FP16 tensor support for improved efficiency. - Update `State` classes and TornadoVM integrations to utilize FP16 data structures for key activation paths.
…maintainability by adding step-by-step comments and simplifying scaled output computation.
…n and remove obsolete hacky methods. - Replace `loadTornadoTensorAsFP32` with `loadTornadoTensor` for cleaner tensor loading. - Add logging for tensor loading details in `loadTornadoTensor`. - Remove `copyHack` method and associated comments from compute kernels and logits layer. - Update `wrapX` state in inference to utilize `asHalfFloatArray` for FP16 support. - Cleanup redundant initialization and tasks in FP16 logits layer.
Member
Author
|
closed in favour of #73 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.