Skip to content

Merge: fix(mllm): concatenate text parts instead of overwriting in chat() #8

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
lubauss merged 1 commit into from
Jan 20, 2026
Merged

Merge: fix(mllm): concatenate text parts instead of overwriting in chat() #8

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 4 additions & 4 deletions vllm_mlx/models/mllm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1044,7 +1044,7 @@ def chat(
# OpenAI multimodal format
for item in content:
if isinstance(item, str):
text_prompt = item
text_prompt += item
continue

# Convert Pydantic models to dicts
Expand All @@ -1057,7 +1057,7 @@ def chat(
item_type = item.get("type", "")

if item_type == "text":
text_prompt = item.get("text", "")
text_prompt += item.get("text", "")

elif item_type == "image_url":
img_url = item.get("image_url", {})
Expand Down Expand Up @@ -1185,7 +1185,7 @@ def stream_chat(
# OpenAI multimodal format
for item in content:
if isinstance(item, str):
text_prompt = item
text_prompt += item
continue

# Convert Pydantic models to dicts
Expand All @@ -1198,7 +1198,7 @@ def stream_chat(
item_type = item.get("type", "")

if item_type == "text":
text_prompt = item.get("text", "")
text_prompt += item.get("text", "")

elif item_type == "image_url":
img_url = item.get("image_url", {})
Expand Down