Skip to content

Sync/videollava #2129

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
astachowiczhabana merged 2 commits into from
Jul 11, 2025
Merged

Sync/videollava #2129

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4ceb9bc
Align VideoLlavaProcessor with Transformers v4.51.3
yafshar Jul 2, 2025
3603f95
Update GaudiVideoLlavaForConditionalGeneration
yafshar Jul 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions examples/video-comprehension/run_example.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,10 +24,10 @@
import numpy as np
import torch
from huggingface_hub import hf_hub_download
from transformers import VideoLlavaProcessor

from optimum.habana.transformers.modeling_utils import (
GaudiVideoLlavaForConditionalGeneration,
GaudiVideoLlavaProcessor,
adapt_transformers_to_gaudi,
)

Expand Down Expand Up @@ -168,7 +168,7 @@ def main():

model = wrap_in_hpu_graph(model)

processor = GaudiVideoLlavaProcessor.from_pretrained(args.model_name_or_path)
processor = VideoLlavaProcessor.from_pretrained(args.model_name_or_path)
processor.tokenizer.padding_side = "left"
inputs = processor(text=prompts, videos=video_clips, return_tensors="pt")
inputs = inputs.to(device)
Expand Down
2 changes: 0 additions & 2 deletions optimum/habana/transformers/modeling_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -183,7 +183,6 @@
GaudiStarcoder2ForCausalLM,
GaudiStarcoder2Model,
GaudiVideoLlavaForConditionalGeneration,
GaudiVideoLlavaProcessor,
GaudiVisionSdpaAttention,
GaudiWav2Vec2SdpaAttention,
GaudiWhisperDecoder,
Expand Down Expand Up @@ -757,7 +756,6 @@ def adapt_transformers_to_gaudi():
transformers.models.video_llava.modeling_video_llava.VideoLlavaForConditionalGeneration = (
GaudiVideoLlavaForConditionalGeneration
)
transformers.models.video_llava.processing_video_llava.VideoLlavaProcessor = GaudiVideoLlavaProcessor

# Optimization for Whisper on Gaudi
transformers.models.whisper.modeling_whisper.WhisperSdpaAttention = GaudiWhisperSdpaAttention
Expand Down
2 changes: 1 addition & 1 deletion optimum/habana/transformers/models/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -339,7 +339,7 @@
gaudi_T5Stack_forward,
)
from .table_transformer import gaudi_table_transformer_conv_encoder_forward
from .video_llava import GaudiVideoLlavaForConditionalGeneration, GaudiVideoLlavaProcessor
from .video_llava import GaudiVideoLlavaForConditionalGeneration
from .vision_encoder_decoder import (
gaudi_VisionEncoderDecoderModel_prepare_inputs_for_generation,
)
Expand Down
1 change: 0 additions & 1 deletion optimum/habana/transformers/models/video_llava/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,2 +1 @@
from .modeling_video_llava import GaudiVideoLlavaForConditionalGeneration
from .processing_video_llava import GaudiVideoLlavaProcessor
Loading