chore(pre-commit): add pre-commit hook to enforce llama_stack logger usage (#3061)

# What does this PR do?

This PR adds a step in pre-commit to enforce using `llama_stack` logger.

Currently, various parts of the code base uses different loggers. As a
custom `llama_stack` logger exist and used in the codebase, it is better
to standardize its utilization.

Signed-off-by: Mustafa Elbehery <melbeher@redhat.com>
Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu>

llama_stack/models/llama/llama3/multimodal/encoder_utils.py

@@ -13,14 +13,15 @@
 
 # Copyright (c) Meta Platforms, Inc. and its affiliates.
 import math
-from logging import getLogger
 
 import torch
 import torch.nn.functional as F
 
+from llama_stack.log import get_logger
+
 from .utils import get_negative_inf_value, to_2tuple
 
-logger = getLogger()
+logger = get_logger(name=__name__, category="models::llama")
 
 
 def resize_local_position_embedding(orig_pos_embed, grid_size):

llama_stack/models/llama/llama3/multimodal/image_transform.py

@@ -13,7 +13,6 @@
 
 import math
 from collections import defaultdict
-from logging import getLogger
 from typing import Any
 
 import torch
@@ -21,9 +20,11 @@ import torchvision.transforms as tv
 from PIL import Image
 from torchvision.transforms import functional as F
 
+from llama_stack.log import get_logger
+
 IMAGE_RES = 224
 
-logger = getLogger()
+logger = get_logger(name=__name__, category="models::llama")
 
 
 class VariableSizeImageTransform:

llama_stack/models/llama/llama3/multimodal/model.py

@@ -3,8 +3,6 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-
-import logging
 import math
 from collections.abc import Callable
 from functools import partial
@@ -22,6 +20,8 @@ from PIL import Image as PIL_Image
 from torch import Tensor, nn
 from torch.distributed import _functional_collectives as funcol
 
+from llama_stack.log import get_logger
+
 from ..model import ModelArgs, RMSNorm, apply_rotary_emb, precompute_freqs_cis
 from .encoder_utils import (
     build_encoder_attention_mask,
@@ -34,9 +34,10 @@ from .encoder_utils import (
 from .image_transform import VariableSizeImageTransform
 from .utils import get_negative_inf_value, to_2tuple
 
-logger = logging.getLogger(__name__)
 MP_SCALE = 8
 
+logger = get_logger(name=__name__, category="models")
+
 
 def reduce_from_tensor_model_parallel_region(input_):
     """All-reduce the input tensor across model parallel group."""
@@ -771,7 +772,7 @@ class TilePositionEmbedding(nn.Module):
         if embed is not None:
             # reshape the weights to the correct shape
             nt_old, nt_old, _, w = embed.shape
-            logging.info(f"Resizing tile embedding from {nt_old}x{nt_old} to {self.num_tiles}x{self.num_tiles}")
+            logger.info(f"Resizing tile embedding from {nt_old}x{nt_old} to {self.num_tiles}x{self.num_tiles}")
             embed_new = TilePositionEmbedding._dynamic_resize(embed, self.num_tiles)
             # assign the weights to the module
             state_dict[prefix + "embedding"] = embed_new

llama_stack/models/llama/llama3/tokenizer.py

@@ -4,8 +4,8 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+
 from collections.abc import Collection, Iterator, Sequence, Set
-from logging import getLogger
 from pathlib import Path
 from typing import (
     Literal,
@@ -14,11 +14,9 @@ from typing import (
 
 import tiktoken
 
+from llama_stack.log import get_logger
 from llama_stack.models.llama.tokenizer_utils import load_bpe_file
 
-logger = getLogger(__name__)
-
-
 # The tiktoken tokenizer can handle <=400k chars without
 # pyo3_runtime.PanicException.
 TIKTOKEN_MAX_ENCODE_CHARS = 400_000
@@ -31,6 +29,8 @@ MAX_NO_WHITESPACES_CHARS = 25_000
 
 _INSTANCE = None
 
+logger = get_logger(name=__name__, category="models::llama")
+
 
 class Tokenizer:
     """

llama_stack/models/llama/llama4/quantization/loader.py

@@ -4,7 +4,6 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-import logging
 import os
 from collections.abc import Callable
 
@@ -13,11 +12,13 @@ from fairscale.nn.model_parallel.initialize import get_model_parallel_rank
 from torch import Tensor, nn
 from torch.nn import functional as F
 
+from llama_stack.log import get_logger
+
 from ...datatypes import QuantizationMode
 from ..model import Transformer, TransformerBlock
 from ..moe import MoE
 
-log = logging.getLogger(__name__)
+log = get_logger(name=__name__, category="models")
 
 
 def swiglu_wrapper_no_reduce(

llama_stack/models/llama/llama4/tokenizer.py

@@ -5,7 +5,6 @@
 # the root directory of this source tree.
 
 from collections.abc import Collection, Iterator, Sequence, Set
-from logging import getLogger
 from pathlib import Path
 from typing import (
     Literal,
@@ -14,11 +13,9 @@ from typing import (
 
 import tiktoken
 
+from llama_stack.log import get_logger
 from llama_stack.models.llama.tokenizer_utils import load_bpe_file
 
-logger = getLogger(__name__)
-
-
 # The tiktoken tokenizer can handle <=400k chars without
 # pyo3_runtime.PanicException.
 TIKTOKEN_MAX_ENCODE_CHARS = 400_000
@@ -101,6 +98,8 @@ BASIC_SPECIAL_TOKENS = [
     "<|fim_suffix|>",
 ]
 
+logger = get_logger(name=__name__, category="models::llama")
+
 
 class Tokenizer:
     """

llama_stack/models/llama/quantize_impls.py

@@ -6,9 +6,10 @@
 
 # type: ignore
 import collections
-import logging
 
-log = logging.getLogger(__name__)
+from llama_stack.log import get_logger
+
+log = get_logger(name=__name__, category="llama")
 
 try:
     import fbgemm_gpu.experimental.gen_ai  # noqa: F401