3 Pull requests merged by 3 people

• Support shape -1 for slice op in the jax backend

  #21501 merged Jul 23, 2025

• Fix RandAugment behavior in tf graph mode

  #21499 merged Jul 22, 2025

• [OpenVINO backend] support take_along_axis

  #21447 merged Jul 21, 2025

11 Pull requests opened by 7 people

• Update compute_output_spec method to support cbrt operation

  #21490 opened Jul 18, 2025

• docs: enhance clarity and consistency in README by correcting platform capitalization

  #21493 opened Jul 21, 2025

• Add Grain integration.

  #21494 opened Jul 21, 2025

• [OpenVINO backend] add supporting for lists and tuples in get_ov_output

  #21495 opened Jul 21, 2025

• [OpenVINO backend] fix_transpose

  #21496 opened Jul 21, 2025

• [OpenVINO backend] fix numpy conversions

  #21498 opened Jul 21, 2025

• Simulated OpenVINO Backend for Testing Unmerged PR Features with Memory Profiling

  #21500 opened Jul 22, 2025

• Docs - Fixed Syntax Error in vectorized_map function example

  #21503 opened Jul 23, 2025

• fix quantization save and load error

  #21504 opened Jul 23, 2025

• fix torch module wrapper serialization error

  #21505 opened Jul 23, 2025

• docs: Keras 3 evaluate() and compiled metrics clarification

  #21506 opened Jul 24, 2025

2 Issues closed by 2 people

• Distributed training with tensorflow doesn't work with Keras 3.7 and above

  #21172 closed Jul 24, 2025

• [bug] keras issue on tpu-vm

  #19448 closed Jul 21, 2025

2 Issues opened by 2 people

• keras.layers.Flatten() not updating shape information after transformation

  #21502 opened Jul 23, 2025

• Training loop from scratch with JAX doesn't converge

  #21489 opened Jul 17, 2025

20 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Keras <> NNX integration

  #21252 commented on Jul 24, 2025 • 12 new comments

• [OpenVINO backend] support export model from the supported backends to openvino format

  #21486 commented on Jul 23, 2025 • 8 new comments

• [OpenVINO Backend] support ops.slice_update

  #21362 commented on Jul 23, 2025 • 3 new comments

• Fix: UpSampling2D bilinear set_image_data_format(channels_first) bug

  #21456 commented on Jul 24, 2025 • 0 new comments

• [OpenVINO backend] support categorical

  #21437 commented on Jul 22, 2025 • 0 new comments

• Running TPU tests on linux-x86-ct6e-44-1tpu

  #21425 commented on Jul 23, 2025 • 0 new comments

• [OpenVINO backend] support tri, triu, and tril

  #21408 commented on Jul 22, 2025 • 0 new comments

• IGNORE THIS PR

  #21389 commented on Jul 20, 2025 • 0 new comments

• Add memory usage monitor callback

  #21245 commented on Jul 23, 2025 • 0 new comments

• Fix TorchModuleWrapper serialization issue

  #20869 commented on Jul 23, 2025 • 0 new comments

• Cannot properly save the model using TorchModuleWrapper and load the model

  #21350 commented on Jul 24, 2025 • 0 new comments

• How does Keras MultiHeadAttention handle input feature dimension vs heads and reshape the output?

  #21219 commented on Jul 23, 2025 • 0 new comments

• ZeroDivisionError: integer modulo by zero | multi-device setup

  #21167 commented on Jul 23, 2025 • 0 new comments

• Integrate Grain into Keras

  #21479 commented on Jul 23, 2025 • 0 new comments

• RematScope with mixed precision: autocast on kernels doesn't seem to trigger on the backwards pass

  #21448 commented on Jul 23, 2025 • 0 new comments

• Trainer.evaluate and Trainer.metrics_names do not interact as specified in the docs

  #21487 commented on Jul 22, 2025 • 0 new comments

• Keras Fails to load quantized model

  #21378 commented on Jul 22, 2025 • 0 new comments

• MaP always 0. Using Yolov8

  #18935 commented on Jul 22, 2025 • 0 new comments

• evaluate() shows incorrect metric values in progress bar vs returned results

  #21301 commented on Jul 21, 2025 • 0 new comments

• 🚀OpenVINO Backend: GFIs for Further Development🚀

  #20910 commented on Jul 20, 2025 • 0 new comments