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
See 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 }}
barhanc
wgpu-executorch
Repository navigation
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
More
items
Perf/kernel optimizations
- #2
#2
Closed
barhanc
wants to merge 13 commits into
main
barhanc/wgpu-executorch:main
from
perf/kernel-optimizations
barhanc/wgpu-executorch:perf/kernel-optimizations
Copy head branch name to clipboard
Conversation
Commits
13
(13)
Checks
Files changed
Closed
Perf/kernel optimizations
#2
barhanc
wants to merge 13 commits into
main
barhanc/wgpu-executorch:main
from
perf/kernel-optimizations
barhanc/wgpu-executorch:perf/kernel-optimizations
Copy head branch name to clipboard
Commits
Commits on Oct 21, 2026
perf(conv): specialize geometry and reuse NCHW output indices
Show description for 3069f75
barhanc
committed
3069f75
View commit details
Copy full SHA for 3069f75
Browse repository at this point
Optimize inference graphs with convolution SiLU fusion and copy aliasing
barhanc
committed
b09fe1f
View commit details
Copy full SHA for b09fe1f
Browse repository at this point
Prototype portable Winograd convolution and validate DepthART speedups
barhanc
committed
7b7eb65
View commit details
Copy full SHA for 7b7eb65
Browse repository at this point
Revert Winograd and graph fusion experiments
barhanc
committed
a62eb22
View commit details
Copy full SHA for a62eb22
Browse repository at this point
Precompute 3x3 convolution tap validity outside accumulation loops
barhanc
committed
6673d3d
View commit details
Copy full SHA for 6673d3d
Browse repository at this point
Profile live inference stages and clarify frame timing
barhanc
committed
e0caea9
View commit details
Copy full SHA for e0caea9
Browse repository at this point
Benchmark model and example stages with controlled paired runs
barhanc
committed
308cc40
View commit details
Copy full SHA for 308cc40
Browse repository at this point
Add narrow 16-row convolution tiles for large spatial grids
barhanc
committed
1c0bb98
View commit details
Copy full SHA for 1c0bb98
Browse repository at this point
Record pointwise and subgroup optimization experiments
barhanc
committed
01e4f13
View commit details
Copy full SHA for 01e4f13
Browse repository at this point
Commits on Oct 22, 2026
Adapt and benchmark published Hugging Face convolution kernels
barhanc
committed
ceb53ab
View commit details
Copy full SHA for ceb53ab
Browse repository at this point
Benchmark native ruNNtime kernels and full vision pipelines
barhanc
committed
5f89b75
View commit details
Copy full SHA for 5f89b75
Browse repository at this point
Correct the ruNNtime DepthART backbone attribution
barhanc
committed
6049402
View commit details
Copy full SHA for 6049402
Browse repository at this point
Specialize small and narrow 3x3 convolutions
barhanc
committed
cdf0f65
View commit details
Copy full SHA for cdf0f65
Browse repository at this point
You can’t perform that action at this time.