Skip to content
Navigation Menu
Sign in
Products
Platform
GitHub
Repository hosting, code review, and collaboration
Copilot
AI coding agent for tasks, projects, and automated work
Build & Ship
Actions
CI/CD and automation
Code Quality
Quality analysis, fixes, and enforcement
Codespaces
Cloud development environments
Secure
Code Security
Vulnerability detection and remediation
Secret Protection
Secret scanning and leak prevention
All Features
Developers
Learn
Documentation
Training
Certifications
Build
Build with Copilot
Customize Copilot
Integrations
Explore
Trending repos
GitHub Sponsors
Developer articles
Changelog
Changelog
Your source for the latest features, improvements, and fixes across GitHub products, all in one place.
Businesses
By Stage
Enterprises
Team
Startups
Nonprofits
By Industry
Healthcare
Financial services
Manufacturing
Government
See all industries
Evaluate GitHub
Why GitHub
Customer Stories
Business insights
Trust Center
Add-ons
GitHub Advanced Security
Enterprise-grade code security
Copilot for business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Resources
Learn & Connect
Documentation
Resource center
Blog
Events & webinars
Community Forum
Customer Stories
Integrations
Support
Customer support
Training
GitHub Status
Company
About
Partners
Changelog
GitHub Universe
GitHub Universe
The event for developers, by developers — talks, workshops, and what’s next for GitHub.
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 }}
generative-computing
granite-switch
Repository navigation
Code
Issues
29
(29)
Pull requests
18
(18)
Actions
Projects
Security and quality
Insights
More
items
Feature/release test tier
- #167
#167
Open
aviv1ron1
wants to merge 13 commits into
main
generative-computing/granite-switch:main
from
feature/release-test-tier
generative-computing/granite-switch:feature/release-test-tier
Copy head branch name to clipboard
Conversation
Commits
13
(13)
Checks
Files changed
Open
Feature/release test tier
#167
aviv1ron1
wants to merge 13 commits into
main
generative-computing/granite-switch:main
from
feature/release-test-tier
generative-computing/granite-switch:feature/release-test-tier
Copy head branch name to clipboard
Commits
Commits on Nov 3, 2026
Pin the default ASR, require it in the config, and add --bundle-asr
Show description for 429175f
aviv1ron1
committed
429175f
View commit details
Copy full SHA for 429175f
Browse repository at this point
Accept any kwargs in the processor tests' get_transcriber stubs
Show description for 2a5f1ce
aviv1ron1
committed
2a5f1ce
View commit details
Copy full SHA for 2a5f1ce
Browse repository at this point
Commits on Nov 4, 2026
Clear the ASR bundle directory before bundling into it
Show description for 481a432
aviv1ron1
committed
481a432
View commit details
Copy full SHA for 481a432
Browse repository at this point
Filter a local ASR source's subdirectories like the Hub download
Show description for 060ac40
aviv1ron1
committed
060ac40
View commit details
Copy full SHA for 060ac40
Browse repository at this point
Bundle the ASR before saving the config that points at it
Show description for 65e882a
aviv1ron1
committed
65e882a
View commit details
Copy full SHA for 65e882a
Browse repository at this point
Normalize asr_bundled_path and keep it inside the checkpoint
Show description for 97032a6
aviv1ron1
committed
97032a6
View commit details
Copy full SHA for 97032a6
Browse repository at this point
Refuse a local --asr-model without --bundle-asr; keep its path private
Show description for baed729
aviv1ron1
committed
baed729
View commit details
Copy full SHA for baed729
Browse repository at this point
Commits on Nov 5, 2026
Add a release test tier and move real-model and matrix GPU tests to it
Show description for 2cf7bf6
aviv1ron1
committed
2cf7bf6
View commit details
Copy full SHA for 2cf7bf6
Browse repository at this point
Run real models only in the release tier; fakes on every PR run
Show description for 3979527
aviv1ron1
committed
3979527
View commit details
Copy full SHA for 3979527
Browse repository at this point
Give the fake bases a complete safetensors index
Show description for 607e03c
aviv1ron1
committed
607e03c
View commit details
Copy full SHA for 607e03c
Browse repository at this point
Make the fake bases' layers matter and their output peaked
Show description for 00c2f4b
aviv1ron1
committed
00c2f4b
View commit details
Copy full SHA for 00c2f4b
Browse repository at this point
Boot each granite4_mini model once: 10 vLLM engines per variant down to 3
Show description for 948a1ea
aviv1ron1
committed
948a1ea
View commit details
Copy full SHA for 948a1ea
Browse repository at this point
Give the fake bases two weight presets: realistic by default, live layers on request
Show description for 4a47cec
aviv1ron1
committed
4a47cec
View commit details
Copy full SHA for 4a47cec
Browse repository at this point
You can’t perform that action at this time.
