423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-14 23:58:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

[misc] update liger-kernel's monkey patch (#7453)

Browse Source 
* Update liger_kernel.py

* Update setup.py
This commit is contained in:
Xiaosu Zhu 2025-03-25 11:58:52 +08:00 committed by GitHub
parent 6d3748f727
commit 6b3b97c738
2 changed files with 2 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
setup.py
View File

@ -46,7 +46,7 @@ extra_require = {
"torch-npu": ["torch==2.4.0", "torch-npu==2.4.0.post2", "decorator"], "torch-npu": ["torch==2.4.0", "torch-npu==2.4.0.post2", "decorator"],
"metrics": ["nltk", "jieba", "rouge-chinese"], "metrics": ["nltk", "jieba", "rouge-chinese"],
"deepspeed": ["deepspeed>=0.10.0,<=0.16.4"], "deepspeed": ["deepspeed>=0.10.0,<=0.16.4"],
"liger-kernel": ["liger-kernel"], "liger-kernel": ["liger-kernel>=0.5.5"],
"bitsandbytes": ["bitsandbytes>=0.39.0"], "bitsandbytes": ["bitsandbytes>=0.39.0"],
"hqq": ["hqq"], "hqq": ["hqq"],
"eetq": ["eetq"], "eetq": ["eetq"],

35
src/llamafactory/model/model_utils/liger_kernel.py
View File

@ -27,39 +27,6 @@ if TYPE_CHECKING:
logger = logging.get_logger(__name__) logger = logging.get_logger(__name__)
def apply_liger_kernel_to_qwen2_5_vl(
rope: bool = True,
cross_entropy: bool = False,
fused_linear_cross_entropy: bool = True,
rms_norm: bool = True,
swiglu: bool = True,
) -> None:
from liger_kernel.transformers import LigerCrossEntropyLoss, LigerRMSNorm, LigerSwiGLUMLP
from liger_kernel.transformers.model.qwen2_vl import lce_forward as qwen2_vl_lce_forward
from liger_kernel.transformers.qwen2vl_mrope import liger_multimodal_rotary_pos_emb
from transformers.models.qwen2_5_vl import modeling_qwen2_5_vl
def get_dtype(self: "modeling_qwen2_5_vl.Qwen2_5_VisionTransformerPretrainedModel"):
return self.dtype
modeling_qwen2_5_vl.Qwen2_5_VisionTransformerPretrainedModel.get_dtype = get_dtype
if rope:
modeling_qwen2_5_vl.apply_multimodal_rotary_pos_emb = liger_multimodal_rotary_pos_emb
if rms_norm:
modeling_qwen2_5_vl.Qwen2RMSNorm = LigerRMSNorm
if cross_entropy:
modeling_qwen2_5_vl.CrossEntropyLoss = LigerCrossEntropyLoss
if fused_linear_cross_entropy:
modeling_qwen2_5_vl.Qwen2_5_VLForConditionalGeneration.forward = qwen2_vl_lce_forward
if swiglu:
modeling_qwen2_5_vl.Qwen2MLP = LigerSwiGLUMLP
def apply_liger_kernel( def apply_liger_kernel(
config: "PretrainedConfig", config: "PretrainedConfig",
model_args: "ModelArguments", model_args: "ModelArguments",
@ -95,7 +62,7 @@ def apply_liger_kernel(
elif model_type == "qwen2_vl": elif model_type == "qwen2_vl":
from liger_kernel.transformers import apply_liger_kernel_to_qwen2_vl as apply_liger_kernel from liger_kernel.transformers import apply_liger_kernel_to_qwen2_vl as apply_liger_kernel
elif model_type == "qwen2_5_vl": elif model_type == "qwen2_5_vl":
apply_liger_kernel = apply_liger_kernel_to_qwen2_5_vl from liger_kernel.transformers import apply_liger_kernel_to_qwen2_5_vl as apply_liger_kernel
else: else:
logger.warning_rank0("Current model does not support liger kernel.") logger.warning_rank0("Current model does not support liger kernel.")
return return