Skip to content
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

Qwen2-VL runtime error fix when prompted with multiple images #2840

Merged
merged 2 commits into from
Dec 17, 2024
Merged

Qwen2-VL runtime error fix when prompted with multiple images #2840

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
6d8cc83
Fix runtime error when Qwen2-VL was prompted with multiple images
alatja Dec 13, 2024
233cbb8
Fix runtime error when Qwen2-VL was prompted with multiple images
alatja Dec 13, 2024
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 server/text_generation_server/models/custom_modeling/qwen2_vl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -450,7 +450,7 @@ def get_position_ids(
width //= self.spatial_merge_size

# calculate the length of the text and image tokens
text_length = next_image_pos - current_pos
text_length = next_image_pos
start_idx = (
llm_pos_ids_list[-1].max() + 1 if llm_pos_ids_list else 0
)
Expand Down Expand Up @@ -480,7 +480,7 @@ def get_position_ids(
)
llm_pos_ids_list.append(image_pos_ids)

current_pos = next_image_pos + time_steps * height * width
current_pos += next_image_pos + time_steps * height * width
image_index += 1

if current_pos < batch_input_ids.size(1):
Expand Down
3 changes: 2 additions & 1 deletion server/text_generation_server/models/vlm_causal_lm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,8 @@ def image_text_replacement(processor, image_input, config, image_id: int) -> str
elif config.model_type == "paligemma":
return "<image>" * config.text_config.num_image_tokens
elif config.model_type == "qwen2_vl":
num_pads = image_input.pixel_values.shape[0] // 4
grid_t, grid_h, grid_w = image_input["image_grid_thw"][image_id]
num_pads = grid_t * grid_h * grid_w // 4
padding = "<|image_pad|>" * num_pads
return f"<|vision_start|>{padding}<|vision_end|>"
else:
Expand Down
Loading