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 }}
NVIDIA
TensorRT-Model-Connect
Repository navigation
Code
Issues
172
(172)
Pull requests
142
(142)
Discussions
Actions
Projects
Security and quality
Insights
More
items
All pull requests
Labels
24
(24)
Milestones
2
(2)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
142
(142)
Closed
1,853
(1,853)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
fix(edge-llm): match native CUDA compiler targets
#2551
·
JCalafato
opened
Nov 20, 2026
Collaborator
·
4 tasks done
·
·
1
perf(qwen): build refitted prefill and decode plans in parallel
#2549
·
yifeif-nv
opened
Nov 20, 2026
Collaborator
·
3 of 11 tasks
·
·
5
perf(whisper): queue each decode step's copies behind the engine
#2538
·
MadFunMaker
opened
Nov 19, 2026
Collaborator
·
2 of 11 tasks
·
·
1
fix(ci): use the Azure Ubuntu mirror in the community CPU image
#2534
·
qikail-ctrl
opened
Nov 19, 2026
Collaborator
·
3 of 11 tasks
·
·
1
1
feat(lfm2): add INT4-AWQ (W4A16) self-quantization for LFM2-1.2B
#2522
·
Moviw
opened
Nov 19, 2026
Contributor
·
3 of 11 tasks
·
·
1
8
perf(nemotron_speech_streaming): read transform factors from tables
#2507
·
MadFunMaker
opened
Nov 18, 2026
Collaborator
·
2 of 11 tasks
·
·
1
perf(nemotron_speech_streaming): cut mel front-end time
#2506
·
MadFunMaker
opened
Nov 18, 2026
Collaborator
·
2 of 11 tasks
·
·
1
fix(modernbert): correct Unicode tokenization
#2505
·
JiaxinD
opened
Nov 18, 2026
Contributor
·
4 of 11 tasks
·
·
1
feat(pika_h3_flex): add Pika-H3-Flex text-to-audio/video
#2504
·
willg-nv
opened
Nov 18, 2026
Collaborator
·
6 of 11 tasks
·
·
1
18
feat(higgs_audio_v2_tokenizer): add Higgs Audio V2 codec decoding
#2497
·
willg-nv
opened
Nov 18, 2026
Collaborator
·
7 of 11 tasks
·
·
1
19
perf(nemotron_speech_streaming): keep the streaming encoder caches on the device
#2490
·
MadFunMaker
opened
Nov 18, 2026
Collaborator
·
2 of 11 tasks
·
·
1
perf(canary): share the feature preparation among threads
#2474
·
MadFunMaker
opened
Nov 18, 2026
Collaborator
·
2 of 11 tasks
·
·
1
perf(whisper): transform the 400-sample mel frame directly
#2473
·
MadFunMaker
opened
Nov 18, 2026
Collaborator
·
2 of 11 tasks
·
·
1
perf(timm_vit): preprocess bicubic images in cropped, fused passes
#2471
·
MadFunMaker
opened
Nov 17, 2026
Collaborator
·
2 of 11 tasks
·
·
1
perf(whisper): project cross-attention K/V once per request in the encoder
#2470
·
MadFunMaker
opened
Nov 17, 2026
Collaborator
·
3 of 11 tasks
·
·
1
perf(whisper): cut host feature-extraction time
#2469
·
MadFunMaker
opened
Nov 17, 2026
Collaborator
·
2 of 11 tasks
·
·
1
fix(ci): retry initial workflow run lookup
#2468
·
JiaxinD
opened
Nov 17, 2026
Contributor
·
3 of 11 tasks
·
·
1
# feat(canary): migrate to semantic Task SDK (#1437)
#2465
·
Darshan3690
opened
Nov 17, 2026
Contributor
·
5 of 11 tasks
·
·
1
17
feat(qwen): add self-contained weightless TensorRT builds
#2463
·
yizhuoz004
opened
Nov 16, 2026
Collaborator
·
6 of 11 tasks
·
·
1
fix(mpnet): correct Unicode normalization and token boundaries
#2458
·
JiaxinD
opened
Nov 16, 2026
Contributor
·
4 of 11 tasks
·
·
2
fix(wav2vec2): trim CTC boundary spaces
#2450
·
JiaxinD
opened
Nov 16, 2026
Contributor
·
3 of 11 tasks
·
·
1
Bringup/cohere transcribe arabic
#2420
·
willg-nv
opened
Nov 13, 2026
Collaborator
·
5 of 11 tasks
·
·
1
5
feat(gpt2): migrate to semantic text_continuation Task SDK
#2383
·
abhirajadhikary06
opened
Nov 12, 2026
·
5 of 11 tasks
·
·
1
17
fix(qwen): match Qwen3 apostrophe pre-tokenization
#2382
·
0z5a
opened
Nov 12, 2026
·
2 of 11 tasks
·
·
1
1
feat(canary): report per-request stage times
#2381
·
MadFunMaker
opened
Nov 12, 2026
Collaborator
·
3 of 11 tasks
·
·
1
Previous
1
2
3
4
5
6
Next
You can’t perform that action at this time.