-
Notifications
You must be signed in to change notification settings - Fork 17.4k
Permalink
Choose a base ref
{{ refName }}
default
Choose a head ref
{{ refName }}
default
Checking mergeability…
Don’t worry, you can still create the pull request.
Comparing changes
Choose two branches to see what’s changed or to start a new pull request.
If you need to, you can also or
learn more about diff comparisons.
Open a pull request
Create a new pull request by comparing changes across two branches. If you need to, you can also .
Learn more about diff comparisons here.
base repository: ggml-org/llama.cpp
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: master
Could not load branches
Nothing to show
Loading
Could not load tags
Nothing to show
{{ refName }}
default
Loading
...
head repository: skmp/llama.cpp
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: master
Could not load branches
Nothing to show
Loading
Could not load tags
Nothing to show
{{ refName }}
default
Loading
- 11 commits
- 6 files changed
- 1 contributor
Commits on Apr 8, 2026
-
add tensor compression and decompression scripts, update .gitignore a…
…nd pyproject.toml
Configuration menu - View commit details
-
Copy full SHA for e93462f - Browse repository at this point
Copy the full SHA e93462fView commit details -
Configuration menu - View commit details
-
Copy full SHA for 07b5df9 - Browse repository at this point
Copy the full SHA 07b5df9View commit details -
add frame rate and vsync options to ffmpeg commands in compress and d…
…ecompress scripts
Configuration menu - View commit details
-
Copy full SHA for 85b56d4 - Browse repository at this point
Copy the full SHA 85b56d4View commit details -
Configuration menu - View commit details
-
Copy full SHA for 04535ef - Browse repository at this point
Copy the full SHA 04535efView commit details -
Configuration menu - View commit details
-
Copy full SHA for f5a03ce - Browse repository at this point
Copy the full SHA f5a03ceView commit details -
Configuration menu - View commit details
-
Copy full SHA for a7b70c4 - Browse repository at this point
Copy the full SHA a7b70c4View commit details -
Configuration menu - View commit details
-
Copy full SHA for 83e1ecc - Browse repository at this point
Copy the full SHA 83e1eccView commit details -
Configuration menu - View commit details
-
Copy full SHA for c9d38d7 - Browse repository at this point
Copy the full SHA c9d38d7View commit details -
Configuration menu - View commit details
-
Copy full SHA for 80ab56b - Browse repository at this point
Copy the full SHA 80ab56bView commit details -
Configuration menu - View commit details
-
Copy full SHA for e709de3 - Browse repository at this point
Copy the full SHA e709de3View commit details -
Enhance GGUF tensor processing scripts
- gguf_compare.py: Added data comparison for shared tensors, including detailed mismatch reporting for the first five tensors. - gguf_compress.py: Updated documentation and added functionality to copy .bin passthrough files during compression. - gguf_decompress.py: Refined BMP reading functions, improved tensor reconstruction for SEM encoding, and enhanced metadata handling. - gguf_tensor_to_image.py: Modified export functionality to handle raw .bin files for float types, improved frame writing, and updated image grouping logic for SEM frames.
Configuration menu - View commit details
-
Copy full SHA for 086be2d - Browse repository at this point
Copy the full SHA 086be2dView commit details
Loading
This comparison is taking too long to generate.
Unfortunately it looks like we can’t render this comparison for you right now. It might be too big, or there might be something weird with your repository.
You can try running this command locally to see the comparison on your machine:
git diff master...master