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
/
Model-Optimizer
Public
Notifications
You must be signed in to change notification settings
Fork
604
Star
3.8k
Code
Issues
93
Pull requests
300
Actions
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Security and quality
Insights
Actions: NVIDIA/Model-Optimizer
Actions
All workflows
Workflows
Example tests
Example tests
GPU tests
GPU tests
Regression tests
Regression tests
Unit tests
Unit tests
.github/workflows/build_puzzletron.yml
.github/workflows/build_puzzletron.yml
Bump uv.lock
Bump uv.lock
Claude
Claude
Claude Code Review
Claude Code Review
Close inactive issues and PRs
Close inactive issues and PRs
Code Quality
Code Quality
Show more workflows...
Management
Caches
Deployments
Unit tests
Unit tests
Actions
Loading...
Loading
Sorry, something went wrong.
Uh oh!
There was an error while loading.
Please reload this page
.
will be ignored since log searching is not yet available
Show workflow options
Create status badge
Create status badge
Loading
Uh oh!
There was an error while loading.
Please reload this page
.
unit_tests.yml
will be ignored since log searching is not yet available
2,500+ workflow runs
2,500+ workflow runs
Event
Filter by Event
Sorry, something went wrong.
Filter
Loading
Sorry, something went wrong.
No matching events.
Status
Filter by Status
Sorry, something went wrong.
Filter
Loading
Sorry, something went wrong.
No matching statuses.
Branch
Filter by Branch
Sorry, something went wrong.
Filter
Loading
Sorry, something went wrong.
No matching branches.
Actor
Filter by Actor
Sorry, something went wrong.
Filter
Loading
Sorry, something went wrong.
No matching users.
Fix hybrid stack spec serialization in Megatron-Bridge checkpoints (#…
Unit tests
#12145:
Commit
b311c05
pushed by
kevalmorabia97
9m 13s
main
main
9m 13s
View workflow file
Reuse a whole recipe via $import, deprecate recipe_type, and start the published-checkpoint backfill with two aliases
Unit tests
#12144:
Pull request
#2376
synchronize by
shengliangxu
19m 28s
shengliangx/batch-backfill-recipe
shengliangx/batch-backfill-recipe
19m 28s
View #2376
View workflow file
Fix hf_ptq.py discarding completed PTQ run on sanity-generate() failure
Unit tests
#12143:
Pull request
#2480
synchronize by
Edwardf0t1
10m 36s
fix/nvbug-6752977-hf-ptq-sanity-generate
fix/nvbug-6752977-hf-ptq-sanity-generate
10m 36s
View #2480
View workflow file
Carry unplaced checkpoint weights using the loader's accounting, replacing MTP name-matching
Unit tests
#12142:
Pull request
#2427
synchronize by
shengliangxu
21m 36s
shengliangx/export-carry-over
shengliangx/export-carry-over
21m 36s
View #2427
View workflow file
Unit tests
Unit tests
#12141:
Scheduled
19m 3s
main
main
19m 3s
View workflow file
[OMNIML-5899] Export IQ checkpoints from HF and Megatron (#2447)
Unit tests
#12140:
Commit
ed5c5ed
pushed by
cjluo-nv
3m 13s
main
main
3m 13s
View workflow file
Fix: Release per-layer expert weights in layerwise export under offload
Unit tests
#12139:
Pull request
#2466
synchronize by
Fridah-nv
21m 36s
fridah/fix-layerwise-export-offload-expert-leak
fridah/fix-layerwise-export-offload-expert-leak
21m 36s
View #2466
View workflow file
Carry unplaced checkpoint weights using the loader's accounting, replacing MTP name-matching
Unit tests
#12138:
Pull request
#2427
synchronize by
shengliangxu
17m 47s
shengliangx/export-carry-over
shengliangx/export-carry-over
17m 47s
View #2427
View workflow file
feat(quantization): register NVFP4 four-over-six as a real calibration algorithm
Unit tests
#12137:
Pull request
#2465
synchronize by
Fridah-nv
22m 1s
fridah/four-over-six-algorithm
fridah/four-over-six-algorithm
22m 1s
View #2465
View workflow file
feat(quantization): register NVFP4 four-over-six as a real calibration algorithm
Unit tests
#12136:
Pull request
#2465
synchronize by
Fridah-nv
5m 50s
fridah/four-over-six-algorithm
fridah/four-over-six-algorithm
5m 50s
View #2465
View workflow file
Carry unplaced checkpoint weights using the loader's accounting, replacing MTP name-matching
Unit tests
#12135:
Pull request
#2427
synchronize by
shengliangxu
21m 13s
shengliangx/export-carry-over
shengliangx/export-carry-over
21m 13s
View #2427
View workflow file
feat(quantization): register NVFP4 four-over-six as a real calibration algorithm
Unit tests
#12134:
Pull request
#2465
synchronize by
Fridah-nv
4m 44s
fridah/four-over-six-algorithm
fridah/four-over-six-algorithm
4m 44s
View #2465
View workflow file
Fix: Release per-layer expert weights in layerwise export under offload
Unit tests
#12133:
Pull request
#2466
synchronize by
Fridah-nv
19m 26s
fridah/fix-layerwise-export-offload-expert-leak
fridah/fix-layerwise-export-offload-expert-leak
19m 26s
View #2466
View workflow file
docs(eval): align Terminal-Bench 2.1 / SWE-bench / MRCR with upstream configs
Unit tests
#12132:
Pull request
#2479
opened by
cjluo-nv
18m 56s
chenjiel/align-eval-skills-tb21-swebench-mrcr
chenjiel/align-eval-skills-tb21-swebench-mrcr
18m 56s
View #2479
View workflow file
Fix HF export crash when a dynamic-block quantizer has zero amax
Unit tests
#12131:
Pull request
#2438
synchronize by
yueshen2016
20m 5s
yueshen/fix-dynamic-zero-amax-export
yueshen/fix-dynamic-zero-amax-export
20m 5s
View #2438
View workflow file
Fix: Release per-layer expert weights in layerwise export under offload
Unit tests
#12130:
Pull request
#2466
synchronize by
Fridah-nv
19m 33s
fridah/fix-layerwise-export-offload-expert-leak
fridah/fix-layerwise-export-offload-expert-leak
19m 33s
View #2466
View workflow file
Drop GDPVal support from the evaluation skill (#2470)
Unit tests
#12129:
Commit
a716696
pushed by
cjluo-nv
8m 48s
main
main
8m 48s
View workflow file
Fix: Release per-layer expert weights in layerwise export under offload
Unit tests
#12128:
Pull request
#2466
synchronize by
Fridah-nv
7m 19s
fridah/fix-layerwise-export-offload-expert-leak
fridah/fix-layerwise-export-offload-expert-leak
7m 19s
View #2466
View workflow file
Fix HF export crash when a dynamic-block quantizer has zero amax
Unit tests
#12127:
Pull request
#2438
synchronize by
yueshen2016
19m 53s
yueshen/fix-dynamic-zero-amax-export
yueshen/fix-dynamic-zero-amax-export
19m 53s
View #2438
View workflow file
Reuse a whole recipe via $import, deprecate recipe_type, and start the published-checkpoint backfill with two aliases
Unit tests
#12126:
Pull request
#2376
synchronize by
shengliangxu
19m 57s
shengliangx/batch-backfill-recipe
shengliangx/batch-backfill-recipe
19m 57s
View #2376
View workflow file
Carry unplaced checkpoint weights using the loader's accounting, replacing MTP name-matching
Unit tests
#12125:
Pull request
#2427
synchronize by
shengliangxu
20m 56s
shengliangx/export-carry-over
shengliangx/export-carry-over
20m 56s
View #2427
View workflow file
Require PTQ recipe guidance before selecting quantization candidates
Unit tests
#12124:
Pull request
#2478
synchronize by
Zhehao-Hu
20m 18s
zhehaoh/feature/quant-recipe-search-ptq-guide
zhehaoh/feature/quant-recipe-search-ptq-guide
20m 18s
View #2478
View workflow file
Require PTQ recipe guidance before selecting quantization candidates
Unit tests
#12123:
Pull request
#2478
opened by
Zhehao-Hu
20m 38s
zhehaoh/feature/quant-recipe-search-ptq-guide
zhehaoh/feature/quant-recipe-search-ptq-guide
20m 38s
View #2478
View workflow file
Reuse a whole recipe via $import, deprecate recipe_type, and start the published-checkpoint backfill with two aliases
Unit tests
#12122:
Pull request
#2376
synchronize by
shengliangxu
20m 53s
shengliangx/batch-backfill-recipe
shengliangx/batch-backfill-recipe
20m 53s
View #2376
View workflow file
Reuse a whole recipe via $import, deprecate recipe_type, and start the published-checkpoint backfill with two aliases
Unit tests
#12121:
Pull request
#2376
synchronize by
shengliangxu
21m 0s
shengliangx/batch-backfill-recipe
shengliangx/batch-backfill-recipe
21m 0s
View #2376
View workflow file
Previous
1
2
3
4
5
…
99
100
101
Next
You can’t perform that action at this time.