mirror of
https://github.com/invoke-ai/InvokeAI.git
synced 2026-04-23 03:00:31 -04:00
fix(mm): vllm model calculates its own size
This commit is contained in:
@@ -47,3 +47,10 @@ class LlavaOnevisionModel(RawModel):
|
||||
|
||||
def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None) -> None:
|
||||
self._vllm_model.to(device=device, dtype=dtype)
|
||||
|
||||
def calc_size(self) -> int:
|
||||
"""Get size of the model in memory in bytes."""
|
||||
# HACK(ryand): Fix this issue with circular imports.
|
||||
from invokeai.backend.model_manager.load.model_util import calc_module_size
|
||||
|
||||
return calc_module_size(self._vllm_model)
|
||||
|
||||
@@ -15,6 +15,7 @@ from invokeai.backend.image_util.depth_anything.depth_anything_pipeline import D
|
||||
from invokeai.backend.image_util.grounding_dino.grounding_dino_pipeline import GroundingDinoPipeline
|
||||
from invokeai.backend.image_util.segment_anything.segment_anything_pipeline import SegmentAnythingPipeline
|
||||
from invokeai.backend.ip_adapter.ip_adapter import IPAdapter
|
||||
from invokeai.backend.llava_onevision_model import LlavaOnevisionModel
|
||||
from invokeai.backend.model_manager.taxonomy import AnyModel
|
||||
from invokeai.backend.onnx.onnx_runtime import IAIOnnxRuntimeModel
|
||||
from invokeai.backend.patches.model_patch_raw import ModelPatchRaw
|
||||
@@ -50,6 +51,7 @@ def calc_model_size_by_data(logger: logging.Logger, model: AnyModel) -> int:
|
||||
SegmentAnythingPipeline,
|
||||
DepthAnythingPipeline,
|
||||
SigLipPipeline,
|
||||
LlavaOnevisionModel,
|
||||
),
|
||||
):
|
||||
return model.calc_size()
|
||||
|
||||
Reference in New Issue
Block a user