Skip to content

Add support for vLLM and local models to GeminiVideoSummarization#436

Open
adsarver wants to merge 43 commits into
developfrom
openai-api-video-summary
Open

Add support for vLLM and local models to GeminiVideoSummarization#436
adsarver wants to merge 43 commits into
developfrom
openai-api-video-summary

Conversation

@adsarver

@adsarver adsarver commented Jul 8, 2026

Copy link
Copy Markdown

kburkewv and others added 30 commits June 27, 2025 14:38
…to motion emphasizer, general linting of spaces
- Now (by default) samples from the video at 1 FPS (hard limit for Gemma4)
- Guarantees frames with moving objects are included and viewable by the model
- Delivers similar performance to previous methods (high FPS, many duplicate frames) while reducing compute
- Maps sampled frames to real frames for timestamp tracking
- Added new motion threshold param (functional equivalent to motion percentile param)
@adsarver
adsarver requested a review from jrobble July 8, 2026 15:04
@adsarver adsarver self-assigned this Jul 8, 2026
…iner, fixed typo in vllm dockerfile, added optional testing at image build without GPU
@adsarver
adsarver force-pushed the openai-api-video-summary branch from 783e4e0 to c28de36 Compare July 13, 2026 14:59
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants