Files
accelerate/tests/test_metrics.py
Ilyas Moutawwakil d9e6af8773 HPU support (#3378)
* init

* style

* is_hpu_available

* fix

* import habana_frameworks.torch.distributed.hccl

* style

* test

* initialize dist proc group

* revert

* set backend to hccl only if hccl initialization sets a local rank

* force backend hccl and multi_hpu type when sure of distributed launch

* style

* pass accelerator tests

* pas big modeling tests with bigger atol/rtol for accelerators

* fix hpu device count and skip tests requiring hpu:x

* hpu autocast

* hpu rng_state

* hpu launch

* hpu special device placement

* hpu launch

* rng state

* distributed data loop tests

* enforce non contiguity after device memory allocation

* pass fsdp tests

* enforce pt_hpu_lazy_mode=0 when fsdp testing

* pass cli tests

* pass and document grad sync tests

* pass kwargs handler and autocast tests

* memory utils

* found source of int64 errors

* skip some modeling utils tests

* enable int64

* skip optimizer tests

* pass checkpointing tests

* pass accelerator tests with safetensors main

* more hpu stuff

* style

* remove PT_HPU_LAZY_MODE and PT_ENABLE_INT64_SUPPORT as they should be in the testing environment

* start testing on gaudi2

* support fp16 on gaudi2

* add testing order

* custom hpu fsdp env dict

* fix torch trace malloc

* test ddp half precision comm hooks

* fix

* fix

* remove lower bound for hpu

* use 0.72 as lower bound

* lower lower bound

* order deepspeed tests

* fix

* deepspeed_use_hpu

* assert non lazy mode with offloaded optimizer

* make patching torch with habana frameworks the default

* less of require_non_hpu

* skip test_multi_device_merge_fsdp_weights for now as it halts

* skip another flaky test

* format

* use habana_visible_modules

* patch torch hpu device count

* avoid setting HABANA_VISIBLE_MODULES

* don't play with habana visible devices/modules

* only with hpu

* fixes and skips

* skip

* fix device ids and add some todos

* skip offloading with generate()

* fix

* reduced atol/rtol for hpu

* fix

* tag deepspeed tests that should run first

* enable a test path that was skipped

* revert a test that was customized for gaudi1

* some patching to enable HABANA_VISIBLE_MODULES

* fix zero3 test

* misc

* test DTensor TP

* remove gaudi1

* test

* style

* comment

* pass pad_across_processes

* require_fp16

* pass memory utils test

* test_ddp_comm_hook

* skip half precision comm hooks on hpu

* fix

* is_fp16_available

* fp16

* tp as part of integration tests

* fix

* write_basic_config

* safetensors

* local sgd and masked_fill_fwd_i64

* fix num_processes in test_load_states_by_steps

* fp8 support

* test

* fix

* add a workflow

* Update src/accelerate/accelerator.py

* review comments

* ci

* style

* comments

* test

* habana_frameworks.torch

* patch device count

* fix

* fix

* require_fp8

* fix

* fix

* gaudi 1

* remove unnecessary

* fixed maskd fill error in transformers

* style

* balanced_memory pass on hpu

* remove for now

* run first

* Apply suggestions from code review

* style after merge

* Update src/accelerate/accelerator.py

Co-authored-by: Zach Mueller <muellerzr@gmail.com>

* Update src/accelerate/utils/transformer_engine.py

Co-authored-by: Zach Mueller <muellerzr@gmail.com>

* empty cache review comments

* test_scirpt.py error messages

* AccelerateTestCase for accelerator state cleanup

* test

* add gaudi1 workflow

* fp8 avilability

* fix

* reduce batch size

* concurrency

* check cuda as well

* nits and comments

* mark fsdp tests that require_fp16

* style

* mark deepspeed fp16 tests

* update image

* fix

* updated

* better msgs

* skip pippy

* test

* test on 2 device

* support up to 1% relative error in test_accelerate

* skip hpu fp16

* allow for 1 byte differene

* revert torch_device change

* style

* skip memory release since it's flaky

* add accelerator state cleanup to fixture

* fix

* atol

* fix

* more rtol

* equal grad test

* revert

* pass pippy on gaudi2 and skip on gaudi1

* enable sd 1.5 test with require fp16

* added warning on memory release

* don't log warning in memory release as it requires PartialState to be initialized

* Apply suggestions from code review

---------

Co-authored-by: Zach Mueller <muellerzr@gmail.com>
2025-03-11 11:16:57 -04:00

64 lines
2.1 KiB
Python

# Copyright 2021 The HuggingFace Team. All rights reserved.
#
# 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
#
# http://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.
import unittest
import numpy as np
from packaging import version
from accelerate import debug_launcher
from accelerate.test_utils import (
DEFAULT_LAUNCH_COMMAND,
device_count,
execute_subprocess_async,
path_in_accelerate_package,
require_cpu,
require_huggingface_suite,
require_multi_device,
require_single_device,
run_first,
)
from accelerate.utils import patch_environment
@require_huggingface_suite
@unittest.skipIf(version.parse(np.__version__) >= version.parse("2.0"), "Test requires numpy version < 2.0")
class MetricTester(unittest.TestCase):
def setUp(self):
self.test_file_path = path_in_accelerate_package("test_utils", "scripts", "external_deps", "test_metrics.py")
from accelerate.test_utils.scripts.external_deps import test_metrics # noqa: F401
self.test_metrics = test_metrics
@require_cpu
def test_metric_cpu_noop(self):
debug_launcher(self.test_metrics.main, num_processes=1)
@require_cpu
def test_metric_cpu_multi(self):
debug_launcher(self.test_metrics.main)
@require_single_device
def test_metric_accelerator(self):
self.test_metrics.main()
@run_first
@require_multi_device
def test_metric_accelerator_multi(self):
print(f"Found {device_count} devices.")
cmd = DEFAULT_LAUNCH_COMMAND + [self.test_file_path]
with patch_environment(omp_num_threads=1, ACCELERATE_LOG_LEVEL="INFO"):
execute_subprocess_async(cmd)