llm-compressor/src/llmcompressor/modeling/__init__.py at 40c6211d1a1c22e6331f9018b687c559827b74db · vllm-project/llm-compressor · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
# ruff: noqa

"""
Model preparation and fusion utilities for compression workflows.

Provides tools for preparing models for compression including
layer fusion, module preparation, and model structure optimization.
Handles pre-compression transformations and architectural modifications
needed for efficient compression.
"""

# trigger registration
from .deepseek_v3 import CalibrationDeepseekV3MoE  # noqa: F401
from .glm4_moe import CalibrationGlm4MoeMoE  # noqa: F401
from .llama4 import SequentialLlama4TextMoe  # noqa: F401
from .qwen3_moe import CalibrationQwen3MoeSparseMoeBlock  # noqa: F401
from .qwen3_vl_moe import CalibrateQwen3VLMoeTextSparseMoeBlock  # noqa: F401
from .qwen3_next_moe import CalibrationQwen3NextSparseMoeBlock  # noqa: F401
from .qwen3_5_vl_moe import CalibrateQwen3_5MoeTextSparseMoeBlock  # noqa: F401
# TODO: add granite4, Qwen3Next

from .fuse import *