Skip to content

Navigation Menu

Appearance settings

- AI CODE CREATION
  GitHub CopilotWrite better code with AI
  GitHub Copilot appDirect agents from issue to merge
  MCP Registry^NewIntegrate external tools
- DEVELOPER WORKFLOWS
  ActionsAutomate any workflow
  CodespacesInstant dev environments
  IssuesPlan and track work
  Code ReviewManage code changes
- APPLICATION SECURITY
  GitHub Advanced SecurityFind and fix vulnerabilities
  Code securitySecure your code as you build
  Secret protectionStop leaks before they start
- EXPLORE
  Why GitHub
  Documentation
  Blog
  Changelog
  Marketplace
View all features
- 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
- 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
- COMMUNITY
  GitHub SponsorsFund open source developers
- PROGRAMS
  Security Lab
  Maintainer Community
  Accelerator
  GitHub Stars
  Archive Program
- REPOSITORIES
  Topics
  Trending
  Collections
- ENTERPRISE SOLUTIONS
  Enterprise platformAI-powered developer platform
- AVAILABLE ADD-ONS
  GitHub Advanced SecurityEnterprise-grade security features
  Copilot for BusinessEnterprise-grade AI features
  Premium SupportEnterprise-grade 24/7 support
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

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

Uh oh!

There was an error while loading. Please reload this page.

ggml-org / llama.cpp Public

Notifications You must be signed in to change notification settings
Fork 20.4k
Star 120k

Code
Issues 672
Pull requests 1.2k
Discussions
Actions
Projects
Wiki
Security and quality 13
Insights

Additional navigation options

Code
Issues
Pull requests
Discussions
Actions
Projects
Wiki
Security and quality
Insights

CUDA: Optimize GDN PP perf#20449

Closed

ORippler wants to merge 12 commits into

ggml-org:gg/gdn-fix-state-transposeggml-org/llama.cpp:gg/gdn-fix-state-transposefrom

ORippler:osimons/gdn-pp-optimizationsORippler/llama.cpp:osimons/gdn-pp-optimizationsCopy head branch name to clipboard

Conversation Commits12 (12)Checks Files changed

Closed

CUDA: Optimize GDN PP perf#20449
ORippler wants to merge 12 commits into
ggml-org:gg/gdn-fix-state-transposefrom
ORippler:osimons/gdn-pp-optimizations

Commits

Commits on Mar 12, 2026

ggml : transpose fused GDN state access for coalesced memory reads (#20436)

authored and
ggerganov
committed
ggml : use SIMD dot products in CPU GDN kernel, couple AR/chunked fused flags

authored and
ggerganov
committed
llama : rever fgdn argument changes
ggerganov
committed
graph : remove GDN state transposes
ggerganov
committed
WIP showing that data-access is the limitation in PP
ORippler
committed
Explicitly prefetch so the compiler knows what is expected of him
ORippler
committed
Add unit-tests for n_tokens % n_tokens_per_loop != 0
ORippler
committed
Handle case where n_tokens % n_tokens_per_loop != 0
ORippler
committed
Account for register pressure of KDA due to per-row g
ORippler
committed
Code cleanup
ORippler
committed
Try adding untailed kernel for speed-ups in KDA setting
ORippler
committed
Pull attn_writes out of the compute loop for no_tail
ORippler
committed

Footer

© 2026 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Community
Docs
Contact

You can’t perform that action at this time.