DAMO-NLP-SG / DAMO-NLP-SG/VideoLLaMA3
Hosting the model
Open
- Dominant language
- Jupyter Notebook
- Stars
- 1.2k
- Forks
- 89
- PR merge metrics
- No merged PRs in 30d
Description
Appreciate all the efforts on the VideoLLaMA model series. I am trying to utilize the model to run inference and ran into out of memory issue. Apparently a 4090 is not enough to host the model. I am wondering in this case, is my only option to host the model on Cloud services like AWS. Appreciate any suggestion!
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue reports an out-of-memory failure when running inference on a 4090 and asks whether AWS is required. Start by reviewing the model's inference and hosting requirements; done would clearly document supported hardware limits and viable hosting options.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- aws
- Domain
- cloud, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100