jax
b38198ef - [jax:ffi] Add `skip_ffi_layout_processing` to `ffi_lowering` so current users of `mlir.custom_call` can migrate to `ffi_lowering` without passing layout information to `hlo.CustomCallOp.build_generic`.

Commit

167 days ago

[jax:ffi] Add `skip_ffi_layout_processing` to `ffi_lowering` so current users of `mlir.custom_call` can migrate to `ffi_lowering` without passing layout information to `hlo.CustomCallOp.build_generic`. PiperOrigin-RevId: 784162644

References

#30252 - [jax:ffi] Add `skip_ffi_layout_processing` to `ffi_lowering` so current users of `mlir.custom_call` can migrate to `ffi_lowering` without passing layout information to `hlo.CustomCallOp.build_generic`.

#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

#33186 - Make nvidia version data optional for ROCm builds

#579 - Create rocm-test-requirements.txt

#580 - GESVDJ support for ROCm GPUs in JAX

#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

Author

danielsuo

Committer

Google-ML-Automation

Parents

21d2433f

jax b38198ef - [jax:ffi] Add `skip_ffi_layout_processing` to `ffi_lowering` so current users of `mlir.custom_call` can migrate to `ffi_lowering` without passing layout information to `hlo.CustomCallOp.build_generic`.

jax
b38198ef - [jax:ffi] Add `skip_ffi_layout_processing` to `ffi_lowering` so current users of `mlir.custom_call` can migrate to `ffi_lowering` without passing layout information to `hlo.CustomCallOp.build_generic`.