rocm_jax/jaxlib/gpu_triton.py
Dan Foreman-Mackey c7ed1bd3a8 Add version check to jaxlib plugin imports.
For the CUDA and ROCM plugins, we only support exact matches between the plugin and jaxlib version, and bad things can happen if we try and load mismatched versions. This change issues a warning and skips importing a plugin when there is a version mismatch.

There are a handful of other places where plugins are imported throughout the JAX codebase (e.g. in lax_numpy, mosaic_gpu, and in the plugins themselves). In a follow up it would be good to add version checking there too, but let's start with just these ones.

PiperOrigin-RevId: 731808733
2025-02-27 11:52:17 -08:00

49 lines
2.0 KiB
Python

# Copyright 2023 The JAX Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from jaxlib import xla_client
from .plugin_support import import_from_plugin
_cuda_triton = import_from_plugin("cuda", "_triton")
_hip_triton = import_from_plugin("rocm", "_triton")
if _cuda_triton:
xla_client.register_custom_call_target(
"triton_kernel_call", _cuda_triton.get_custom_call(),
platform='CUDA')
TritonKernelCall = _cuda_triton.TritonKernelCall
TritonAutotunedKernelCall = _cuda_triton.TritonAutotunedKernelCall
TritonKernel = _cuda_triton.TritonKernel
create_array_parameter = _cuda_triton.create_array_parameter
create_scalar_parameter = _cuda_triton.create_scalar_parameter
get_compute_capability = _cuda_triton.get_compute_capability
get_arch_details = _cuda_triton.get_arch_details
get_custom_call = _cuda_triton.get_custom_call
get_serialized_metadata = _cuda_triton.get_serialized_metadata
if _hip_triton:
xla_client.register_custom_call_target(
"triton_kernel_call", _hip_triton.get_custom_call(),
platform='ROCM')
TritonKernelCall = _hip_triton.TritonKernelCall
TritonAutotunedKernelCall = _hip_triton.TritonAutotunedKernelCall
TritonKernel = _hip_triton.TritonKernel
create_array_parameter = _hip_triton.create_array_parameter
create_scalar_parameter = _hip_triton.create_scalar_parameter
get_compute_capability = _hip_triton.get_compute_capability
get_arch_details = _hip_triton.get_arch_details
get_custom_call = _hip_triton.get_custom_call
get_serialized_metadata = _hip_triton.get_serialized_metadata