jax
b47fa65c - Merge pull request #30040 from mattjj:direct-linearize-fixes-5

Commit

193 days ago

Merge pull request #30040 from mattjj:direct-linearize-fixes-5 PiperOrigin-RevId: 782091646

References

#30040 - [direct-linearize] fix tests to pass under JAX_USE_DIRECT_LINEARIZE=1

#31381 - Remove old ROCm build code

#31720 - Fix ann_test.py numerical bug in target reshape

#31768 - [ROCm] Support lowering through PJRT_Triton_Extension

#32115 - Relax version requirements for ROCm Jax Plugin wheels

#33157 - Resolve undefined behavior in bitshift unit test

#579 - Create rocm-test-requirements.txt

#581 - Fix/pallas tests shared memory

#584 - Use plain bazel to test jax, use hermetic rocm dependency

#585 - update a test for checking zero ROCm GPU event

#34135 - [ROCm] update to test if there are GPU events when doing profiling on…

#587 - Mark ROCm support for gtsv2 as stable

#591 - Adding run_pytest_rocm.sh

#592 - Upstream ci download jax rocm wheels

#34304 - [ROCm] Add ROCm platform support for psend/precv collective operations

#599 - Use xla from rocm-jaxlib-v0.8.0 release branch

#604 - Add proper ROCm skip for cuDNN attention tests

#34450 - [ROCm] Upstream ROCm CI Nightly Wheel Testing

#611 - Enable test_comparison_scalar tests for ROCm GPUs

#34470 - Enabled testTridiagonal for ROCm devices.

#34474 - Added support for GESVDJ on ROCm devices

#614 - Implement approx_tanh for ROCm using OCML tanh function

#34494 - Enabled ROCm devices to default to Jacobi SVD on smaller matrices.

#626 - Enabled triton_pallas_test.py unit test file to run

Author

Google-ML-Automation

Google-ML-Automation

Parents

Loading