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
/
TensorRT-LLM
Public
Notifications
You must be signed in to change notification settings
Fork
2.8k
Star
14.7k
Code
Issues
606
Pull requests
902
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
[None][perf] optimize encoder-decoder PyTorch performance
- #16706
#16706
Merged
cascade812
merged 22 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
cascade812:guiju/encoder-decoder-perf
cascade812/TensorRT-LLM:guiju/encoder-decoder-perf
Copy head branch name to clipboard
Aug 9, 2026
Conversation
Commits
22
(22)
Checks
Files changed
Merged
[None][perf] optimize encoder-decoder PyTorch performance
#16706
cascade812
merged 22 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
cascade812:guiju/encoder-decoder-perf
cascade812/TensorRT-LLM:guiju/encoder-decoder-perf
Copy head branch name to clipboard
Commits
Commits on Jul 21, 2026
[None][perf] accumulate encoder work during decode
Show description for 1cc01f1
cascade812
committed
1cc01f1
View commit details
Copy full SHA for 1cc01f1
Browse repository at this point
[None][perf] prepare mixed decoder batches natively
Show description for 6fd8dc8
cascade812
committed
6fd8dc8
View commit details
Copy full SHA for 6fd8dc8
Browse repository at this point
Commits on Jul 22, 2026
[None][perf] reuse stable greedy sampling metadata
Show description for 433dcb9
cascade812
committed
433dcb9
View commit details
Copy full SHA for 433dcb9
Browse repository at this point
Commits on Jul 26, 2026
[None][perf] optimize BART encoder-decoder execution
Show description for f3a8e10
cascade812
committed
f3a8e10
View commit details
Copy full SHA for f3a8e10
Browse repository at this point
Commits on Jul 29, 2026
[None][perf] enable encoder CUDA graphs for encoder-decoder models
Show description for ebccb5d
cascade812
committed
ebccb5d
View commit details
Copy full SHA for ebccb5d
Browse repository at this point
Merge origin/main into guiju/encoder-decoder-perf
Show description for 0b6cc7c
cascade812
committed
0b6cc7c
View commit details
Copy full SHA for 0b6cc7c
Browse repository at this point
Commits on Jul 30, 2026
[None][perf] improve encoder-decoder CUDA graph handling
Show description for 04ca506
cascade812
committed
04ca506
View commit details
Copy full SHA for 04ca506
Browse repository at this point
[None][fix] stabilize encoder-decoder CUDA graph capture
Show description for 4f981ac
cascade812
committed
4f981ac
View commit details
Copy full SHA for 4f981ac
Browse repository at this point
Merge origin/main into guiju/encoder-decoder-perf
Show description for 0c32c18
cascade812
committed
0c32c18
View commit details
Copy full SHA for 0c32c18
Browse repository at this point
Commits on Jul 31, 2026
[None][fix] stabilize encoder-decoder CUDA graph replay
Show description for eca64fd
cascade812
committed
eca64fd
View commit details
Copy full SHA for eca64fd
Browse repository at this point
Merge branch 'main' into guiju/encoder-decoder-perf
Show description for 336168c
cascade812
authored
336168c
View commit details
Copy full SHA for 336168c
Browse repository at this point
Commits on Aug 1, 2026
address comments
Show description for bb70aab
cascade812
committed
bb70aab
View commit details
Copy full SHA for bb70aab
Browse repository at this point
Merge remote-tracking branch 'origin/main' into guiju/encoder-decoder-perf
Show description for a2a73ce
cascade812
committed
a2a73ce
View commit details
Copy full SHA for a2a73ce
Browse repository at this point
Commits on Aug 3, 2026
Merge branch 'main' into guiju/encoder-decoder-perf
Show description for b68b955
cascade812
authored
b68b955
View commit details
Copy full SHA for b68b955
Browse repository at this point
address comment
Show description for 15b2d67
cascade812
committed
15b2d67
View commit details
Copy full SHA for 15b2d67
Browse repository at this point
Commits on Aug 4, 2026
fix failed tests
Show description for b7b15eb
cascade812
committed
b7b15eb
View commit details
Copy full SHA for b7b15eb
Browse repository at this point
address failed tests
Show description for 477ac44
cascade812
committed
477ac44
View commit details
Copy full SHA for 477ac44
Browse repository at this point
Commits on Aug 5, 2026
address comments
Show description for 47b0116
cascade812
committed
47b0116
View commit details
Copy full SHA for 47b0116
Browse repository at this point
Merge remote-tracking branch 'origin/main' into guiju/encoder-decoder-perf
Show description for 01ae2d2
cascade812
committed
01ae2d2
View commit details
Copy full SHA for 01ae2d2
Browse repository at this point
Commits on Aug 6, 2026
fix failed test
Show description for 42c8bff
cascade812
committed
42c8bff
View commit details
Copy full SHA for 42c8bff
Browse repository at this point
Commits on Aug 7, 2026
address comment
Show description for 0789f21
cascade812
committed
0789f21
View commit details
Copy full SHA for 0789f21
Browse repository at this point
Merge branch 'main' into guiju/encoder-decoder-perf
cascade812
authored
51f1037
View commit details
Copy full SHA for 51f1037
Browse repository at this point
You can’t perform that action at this time.