Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Pricing
Search
/
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
NVIDIA
/
cosmos-framework
Public
Notifications
You must be signed in to change notification settings
Fork
148
Star
539
Code
Issues
14
Pull requests
13
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
feat(vlm): LoRA SFT support for VLM + VideoPhy-2 LoRA recipes
- #155
#155
Open
lfengad
wants to merge 9 commits into
main
NVIDIA/cosmos-framework:main
from
liangf/vlm-lora-sft
NVIDIA/cosmos-framework:liangf/vlm-lora-sft
Copy head branch name to clipboard
Conversation
Commits
9
(9)
Checks
Files changed
Open
feat(vlm): LoRA SFT support for VLM + VideoPhy-2 LoRA recipes
#155
lfengad
wants to merge 9 commits into
main
NVIDIA/cosmos-framework:main
from
liangf/vlm-lora-sft
NVIDIA/cosmos-framework:liangf/vlm-lora-sft
Copy head branch name to clipboard
Commits
Commits on Sep 18, 2026
feat(vlm): LoRA SFT support for VLM + VideoPhy-2 LoRA recipes
Show description for 779af8f
lfengad
and
claude
committed
779af8f
View commit details
Copy full SHA for 779af8f
Browse repository at this point
feat(vlm): merge LoRA adapters into base weights on HF export
Show description for cf669d0
lfengad
and
claude
committed
cf669d0
View commit details
Copy full SHA for cf669d0
Browse repository at this point
refactor(vlm): drop videophy2_z_lora, drive LoRA from the TOMLs
Show description for 5c3a43a
lfengad
and
claude
committed
5c3a43a
View commit details
Copy full SHA for 5c3a43a
Browse repository at this point
test(vlm): assert the LoRA merge completed, and verify it under FSDP2
Show description for 99beb81
lfengad
and
claude
committed
99beb81
View commit details
Copy full SHA for 99beb81
Browse repository at this point
refactor(vlm): drop the nano LoRA recipe, keep super + edge
Show description for fcdef7b
lfengad
and
claude
committed
fcdef7b
View commit details
Copy full SHA for fcdef7b
Browse repository at this point
docs: cover VLM LoRA, and drop the now-false "VFM only" on lora_*
Show description for bd7ed35
lfengad
and
claude
committed
bd7ed35
View commit details
Copy full SHA for bd7ed35
Browse repository at this point
docs: align table columns to satisfy rumdl-fmt
Show description for bbfa8f6
lfengad
and
claude
committed
bbfa8f6
View commit details
Copy full SHA for bbfa8f6
Browse repository at this point
refactor(vlm): drop the LoRA defensive guards from vlm_model
Show description for 4f41481
lfengad
and
claude
committed
4f41481
View commit details
Copy full SHA for 4f41481
Browse repository at this point
fix(vlm): enforce LoRA-only trainability
lfengad
committed
a532fb6
View commit details
Copy full SHA for a532fb6
Browse repository at this point
You can’t perform that action at this time.