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 }}
Uh oh!
There was an error while loading.
Please reload this page
.
NVIDIA
/
TensorRT-LLM
Public
Notifications
You must be signed in to change notification settings
Fork
2.7k
Star
14.6k
Code
Issues
584
Pull requests
872
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
[None][feat] Support image input in the Triton llmapi backend
- #18381
#18381
Merged
faradawn
merged 10 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
faradawn:feat/triton-llmapi-multimodal-image
faradawn/TensorRT-LLM:feat/triton-llmapi-multimodal-image
Copy head branch name to clipboard
Sep 10, 2026
Conversation
Commits
10
(10)
Checks
Files changed
Merged
[None][feat] Support image input in the Triton llmapi backend
#18381
faradawn
merged 10 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
faradawn:feat/triton-llmapi-multimodal-image
faradawn/TensorRT-LLM:feat/triton-llmapi-multimodal-image
Copy head branch name to clipboard
Commits
Commits on Aug 28, 2026
[None][feat] Support image input in the Triton llmapi backend
Show description for 881d964
faradawn
and
claude
committed
881d964
View commit details
Copy full SHA for 881d964
Browse repository at this point
Commits on Sep 1, 2026
[None][feat] Use the trtllm-serve multimodal path in the Triton llmapi backend
Show description for 80fd452
faradawn
committed
80fd452
View commit details
Copy full SHA for 80fd452
Browse repository at this point
[None][feat] Keep the Triton llmapi multimodal path working on TRT-LLM 1.2.1
Show description for c41fc3e
faradawn
committed
c41fc3e
View commit details
Copy full SHA for c41fc3e
Browse repository at this point
Commits on Sep 4, 2026
[None][fix] Import test symbols explicitly to satisfy ruff F405
Show description for 54c65ef
faradawn
committed
54c65ef
View commit details
Copy full SHA for 54c65ef
Browse repository at this point
[None][fix] Drop the redundant star import from the llmapi backend tests
Show description for 41134c3
faradawn
committed
41134c3
View commit details
Copy full SHA for 41134c3
Browse repository at this point
[None][fix] Report preprocessing failures instead of hanging the client
Show description for f1166de
faradawn
committed
f1166de
View commit details
Copy full SHA for f1166de
Browse repository at this point
[None][feat] Share the multimodal request-building path with trtllm-serve
Show description for bc250d5
faradawn
committed
bc250d5
View commit details
Copy full SHA for bc250d5
Browse repository at this point
Commits on Sep 8, 2026
[None][fix] Accept only remote and inline image_url values
Show description for 7149760
faradawn
committed
7149760
View commit details
Copy full SHA for 7149760
Browse repository at this point
[None][doc] Document the allowed scope of image_url access
Show description for 0a71057
faradawn
committed
0a71057
View commit details
Copy full SHA for 0a71057
Browse repository at this point
[None][fix] Restrict image_url to http(s) URLs
Show description for 56d32b0
faradawn
committed
56d32b0
View commit details
Copy full SHA for 56d32b0
Browse repository at this point
You can’t perform that action at this time.