-
Notifications
You must be signed in to change notification settings - Fork 12.2k
Comparing changes
Open a pull request
base repository: ggml-org/llama.cpp
base: master@{1day}
head repository: ggml-org/llama.cpp
compare: master
- 10 commits
- 16 files changed
- 8 contributors
Commits on Jul 1, 2025
-
Configuration menu - View commit details
-
Copy full SHA for 79b33b2 - Browse repository at this point
Copy the full SHA 79b33b2View commit details -
ggml-quants : rename best_mad to best_error (ggml/1283)
This commit renames the variable `best_mad` to `best_error` in the `make_qkx2_quants` function. The motivation for this is that the name `best_mad` can be somewhat confusing if mean absolute deviation (MAD) is not in use.
Configuration menu - View commit details
-
Copy full SHA for 497be7c - Browse repository at this point
Copy the full SHA 497be7cView commit details -
ggml-cpu : "align corners" for bilinear upscale/downscale (ggml/1285)
* add "align corners" mode for bilinear upscale, and allow downscaling * add ggml_interpolate, deprecate ggml_upscale_ext, pass in align-corners as bit-flag * test-backend-ops: replace ggml_upscale_ext with ggml_interpolate, add test cases for downscale and align-corners
Configuration menu - View commit details
-
Copy full SHA for 431b2c2 - Browse repository at this point
Copy the full SHA 431b2c2View commit details -
Configuration menu - View commit details
-
Copy full SHA for f61c05d - Browse repository at this point
Copy the full SHA f61c05dView commit details -
Configuration menu - View commit details
-
Copy full SHA for a6a4795 - Browse repository at this point
Copy the full SHA a6a4795View commit details -
Configuration menu - View commit details
-
Copy full SHA for eff5e45 - Browse repository at this point
Copy the full SHA eff5e45View commit details -
Configuration menu - View commit details
-
Copy full SHA for 6a746cf - Browse repository at this point
Copy the full SHA 6a746cfView commit details -
CANN: update aclnnGroupedMatmulV2 to aclnnGroupedMatmulV3 (#14411)
* [CANN]update to aclnnGroupedMatmulV2 Signed-off-by: noemotiovon <[email protected]> * Support MUL_MAT_ID on 310p Signed-off-by: noemotiovon <[email protected]> * fix editorconfig Signed-off-by: noemotiovon <[email protected]> --------- Signed-off-by: noemotiovon <[email protected]>
Configuration menu - View commit details
-
Copy full SHA for 343b6e9 - Browse repository at this point
Copy the full SHA 343b6e9View commit details -
Add Vulkan images to docker.md (#14472)
Right now it's not easy to find those.
Configuration menu - View commit details
-
Copy full SHA for 1b2aaf2 - Browse repository at this point
Copy the full SHA 1b2aaf2View commit details -
ci : disable fast-math for Metal GHA CI (#14478)
* ci : disable fast-math for Metal GHA CI ggml-ci * cont : remove -g flag ggml-ci
Configuration menu - View commit details
-
Copy full SHA for de56944 - Browse repository at this point
Copy the full SHA de56944View commit details
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@{1day}...master