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 }}
PaddlePaddle
/
FastDeploy
Public
Notifications
You must be signed in to change notification settings
Fork
756
Star
3.7k
Code
Issues
246
Pull requests
394
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
Opt wint2
- #2741
#2741
Closed
baoqiwen
wants to merge 20 commits into
PaddlePaddle:develop
PaddlePaddle/FastDeploy:develop
from
baoqiwen:opt_wint2
baoqiwen/FastDeploy:opt_wint2
Copy head branch name to clipboard
Conversation
Commits
20
(20)
Checks
Files changed
Closed
Opt wint2
#2741
baoqiwen
wants to merge 20 commits into
PaddlePaddle:develop
PaddlePaddle/FastDeploy:develop
from
baoqiwen:opt_wint2
baoqiwen/FastDeploy:opt_wint2
Copy head branch name to clipboard
Commits
Commits on Jul 1, 2025
Change wint2 to ColumnMajor.
Show description for fbd86c8
Xreki
committed
fbd86c8
View commit details
Copy full SHA for fbd86c8
Browse repository at this point
Unify default_wint2x_mma.
Show description for 2efcfbb
Xreki
committed
2efcfbb
View commit details
Copy full SHA for 2efcfbb
Browse repository at this point
Commits on Jul 2, 2025
Change wint2 to ColumnMajorTileInterleave.
Show description for feac956
Xreki
committed
feac956
View commit details
Copy full SHA for feac956
Browse repository at this point
Enable async copy for B.
Show description for da648e8
Xreki
committed
da648e8
View commit details
Copy full SHA for da648e8
Browse repository at this point
Commits on Jul 8, 2025
Add wint2x Dequantizer
baoqiwen
committed
8c6fa14
View commit details
Copy full SHA for 8c6fa14
Browse repository at this point
Remove TileDequanterB related codes.
Show description for 5ce3424
Xreki
committed
5ce3424
View commit details
Copy full SHA for 5ce3424
Browse repository at this point
Merge branch 'opt_wint2' of https://github.com/baoqiwen/FastDeploy into opt_wint2
Show description for 487d643
Xreki
committed
487d643
View commit details
Copy full SHA for 487d643
Browse repository at this point
Implement FastInterleavedAndBiasedNumericArrayConverter for wint2.
Show description for 2bda35d
Xreki
committed
2bda35d
View commit details
Copy full SHA for 2bda35d
Browse repository at this point
Commits on Jul 14, 2025
Implement Wint2ParamsAccessor to load extra quant params from global memory.
Show description for e86c13d
Xreki
committed
e86c13d
View commit details
Copy full SHA for e86c13d
Browse repository at this point
Commits on Jul 15, 2025
Implement FastInterleavedAndBiasedNumericArrayConverter for wint2.
Show description for 0b60689
Xreki
authored and
baoqiwen
committed
0b60689
View commit details
Copy full SHA for 0b60689
Browse repository at this point
Use async copy for local_scale.
Show description for 0fabdbc
Xreki
committed
0fabdbc
View commit details
Copy full SHA for 0fabdbc
Browse repository at this point
Merge branch 'opt_wint2' of https://github.com/baoqiwen/FastDeploy into opt_wint2
Show description for 5715889
Xreki
committed
5715889
View commit details
Copy full SHA for 5715889
Browse repository at this point
Merge branch 'opt_wint2' of https://github.com/baoqiwen/FastDeploy into opt_wint2
Show description for 81c704b
Xreki
authored and
baoqiwen
committed
81c704b
View commit details
Copy full SHA for 81c704b
Browse repository at this point
Merge branch 'opt_wint2' of https://github.com/baoqiwen/FastDeploy into opt_wint2
Show description for 567c4bf
Xreki
committed
567c4bf
View commit details
Copy full SHA for 567c4bf
Browse repository at this point
Commits on Jul 16, 2025
Check and correct the load and dequantize of weights.
Show description for 79b8d51
Xreki
committed
79b8d51
View commit details
Copy full SHA for 79b8d51
Browse repository at this point
Change for performance tuning.
Show description for 43eb19d
Xreki
committed
43eb19d
View commit details
Copy full SHA for 43eb19d
Browse repository at this point
Optimize the global memory access size of local_scale reading.
Show description for 22d5a5d
Xreki
committed
22d5a5d
View commit details
Copy full SHA for 22d5a5d
Browse repository at this point
Commits on Jul 17, 2025
Specialize mma_tensor_op for wint2 to enable fine-grained pipeline.
Show description for 367422e
Xreki
committed
367422e
View commit details
Copy full SHA for 367422e
Browse repository at this point
Minor fix.
Show description for 3caf310
Xreki
committed
3caf310
View commit details
Copy full SHA for 3caf310
Browse repository at this point
Commits on Jul 18, 2025
optimizing dequant performance with LOP3
RbRe145
committed
85e337a
View commit details
Copy full SHA for 85e337a
Browse repository at this point
You can’t perform that action at this time.
