jax
bba6c7e3 - [Mosaic GPU] Respect `packing` for TMEM scratch allocation.

Commit

159 days ago

[Mosaic GPU] Respect `packing` for TMEM scratch allocation. This change ensures that the `packing` parameter is correctly propagated to the `tmem_alloc` dialect operation and used in the calculation of the number of columns for Warpgroup lowering semantics. PiperOrigin-RevId: 796316623

References

#31062 - [Mosaic GPU] Respect `packing` for TMEM scratch allocation.

#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 - [ROCm] 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…

#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

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

#34470 - [ROCm] Enabled testTridiagonal for ROCm devices.

#34474 - [ROCm] Added support for GESVDJ on ROCm devices

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

#632 - Add script for running bazel tests on ROCm

#638 - Support wheels as build deps

#34561 - [ROCm] Enable ToeplitzSymmetricConstruction and condition number tests

#34567 - [ROCm]Unskip testMultivariateNormalSingularCovariance on ROCm

#34568 - [ROCm] Skip test_tridiagonal_solve on ROCm

#34575 - [ROCm] Enabled the Triton Pallas tests to run for ROCm.

#34577 - [ROCm] Enabled RNN unit test "test_no_workspace_overflow" for ROCm.

#34578 - [ROCm] Unskip supported dtypes for testConvolutionsPreferredElementType on ROCm

#34598 - Implement approx_tanh for ROCm using OCML tanh function

#34600 - Enable scaled_matmul tests on ROCm

#34601 - Enable neural network tests on ROCm

#34602 - Fix and enable Pallas ops tests on ROCm

#34603 - Enable miscellaneous tests on ROCm

#654 - Skip test_batch_axis_sharding_jvp on ROCm

#34615 - [ROCm] Skip test_batch_axis_sharding_jvp on ROCm

Author

allanrenucci

allanrenucci

Committer

Google-ML-Automation

Google-ML-Automation

Parents

Loading