Skip to content

Navigation Menu

Explore
By company size
By use case
By industry
View all solutions
Topics
- AI
- DevOps
- Security
- Software Development
- View all
Explore
- GitHub Sponsors
  Fund open source developers
- The ReadME Project
  GitHub community articles
Repositories
- Enterprise platform
  AI-powered developer platform
Available add-ons
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.

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

ggml-org / llama.cpp Public

Notifications You must be signed in to change notification settings
Fork 10.9k
Star 75.6k

Code
Issues 344
Pull requests 387
Discussions
Actions
Projects 9
Wiki
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Discussions
Actions
Projects
Wiki
Security
Insights

ggml backends interface, ggml-cuda refactor#2239

Closed

slaren wants to merge 21 commits intomasterggml-org/llama.cpp:masterfrom ggml-backendsggml-org/llama.cpp:ggml-backendsCopy head branch name to clipboard

+4,743-4,531

Conversation Commits21 (21)Checks Files changed

Commits

Commits on Jul 16, 2023

ggml backend interface wip
slaren
committed
restore simple.cpp for now
slaren
committed
minor fixes
slaren
committed
fix NVCC version on Makefile, __halves2half2 -> make_half2
slaren
committed
rebase to master (except ggml-cuda)
slaren
committed

Commits on Jul 17, 2023

only allocate as much memory as is required in each backend for the model
slaren
committed
improve layer backend printing with ranges
slaren
committed
fix double-free with --no-mmap
slaren
committed

Commits on Jul 19, 2023

allocators wip
slaren
committed
llama.cpp: remove backend-specific code where possible
slaren
committed

Commits on Jul 20, 2023

automatically calculate compute buffer sizes (without graph allocator)
slaren
committed
initial implementation of delayed graph allocation
slaren
committed
improved memory management
slaren
committed

Commits on Jul 21, 2023

remove unused code
slaren
committed
llama.cpp: partially restore state support, graph export
slaren
committed
improved memory management fixes
slaren
committed
allocator: automatic inplace operations
slaren
committed

Commits on Jul 22, 2023

allocator: fix partial offloading
slaren
committed
allocator cleanup
slaren
committed
llama.cpp: print input/output buffers size
slaren
committed
allocator: cleanup, more comments
slaren
committed

Footer

© 2025 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Docs
Contact

You can’t perform that action at this time.