build: format codebase imports using ruff linter (#1028)

# What does this PR do?

- Configured ruff linter to automatically fix import sorting issues.
- Set --exit-non-zero-on-fix to ensure non-zero exit code when fixes are
applied.
- Enabled the 'I' selection to focus on import-related linting rules.
- Ran the linter, and formatted all codebase imports accordingly.
- Removed the black dep from the "dev" group since we use ruff

Signed-off-by: Sébastien Han <seb@redhat.com>

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
[Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.*]

[//]: # (## Documentation)
[//]: # (- [ ] Added a Changelog entry if the change is significant)

Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han 2025-02-13 19:06:21 +01:00 committed by GitHub
parent 1527c30107
commit e4a1579e63
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
140 changed files with 139 additions and 243 deletions

View file

@ -8,7 +8,6 @@
# This software may be used and distributed in accordance with the terms of the Llama 3 Community License Agreement.
import collections
import logging
from typing import Optional, Type
@ -23,7 +22,7 @@ except ImportError:
raise
import torch
from torch import nn, Tensor
from torch import Tensor, nn
class Fp8ScaledWeights:

View file

@ -10,9 +10,9 @@
import unittest
import torch
from fp8_impls import ffn_swiglu_fp8_dynamic, FfnQuantizeMode, quantize_fp8
from hypothesis import given, settings, strategies as st
from fp8_impls import FfnQuantizeMode, ffn_swiglu_fp8_dynamic, quantize_fp8
from hypothesis import given, settings
from hypothesis import strategies as st
from torch import Tensor

View file

@ -12,18 +12,13 @@ import os
from typing import Any, Dict, List, Optional
import torch
from fairscale.nn.model_parallel.layers import ColumnParallelLinear, RowParallelLinear
from fairscale.nn.model_parallel.mappings import reduce_from_model_parallel_region
from llama_models.datatypes import CheckpointQuantizationFormat
from llama_models.llama3.api.args import ModelArgs
from llama_models.llama3.reference_impl.model import Transformer, TransformerBlock
from llama_models.sku_list import resolve_model
from torch import nn, Tensor
from torch import Tensor, nn
from torchao.quantization.GPTQ import Int8DynActInt4WeightLinear
from llama_stack.apis.inference import QuantizationType

View file

@ -16,14 +16,12 @@ from pathlib import Path
from typing import Optional
import fire
import torch
from fairscale.nn.model_parallel.initialize import (
get_model_parallel_rank,
initialize_model_parallel,
model_parallel_is_initialized,
)
from llama_models.llama3.api.args import ModelArgs
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_models.llama3.reference_impl.model import Transformer, TransformerBlock