b0d47f2ea7
Fix linters issues in editorconfig-checker job
...
https://github.com/ggml-org/llama.cpp/actions/runs/19548770247/job/55974800633?pr=17413
2025-11-20 15:19:41 -08:00
d7da9ea9a8
Merge branch 'ggml-master' into ai-chat-binding-2
2025-11-20 11:14:18 -08:00
254cd841b2
Remove cpu_features
2025-11-20 10:21:00 -08:00
196f5083ef
common : more accurate sampling timing ( #17382 )
...
* common : more accurate sampling timing
* eval-callback : minor fixes
* cont : add time_meas impl
* cont : fix log msg [no ci]
* cont : fix multiple definitions of time_meas
* llama-cli : exclude chat template init from time measurement
* cont : print percentage of unaccounted time
* cont : do not reset timings
2025-11-20 13:40:10 +02:00
5886f4f545
examples(gguf): GGUF example outputs ( #17025 )
...
* feat(llama-gguf): Print out the tensor type in llama-gguf r
Branch: Mamba2Perf
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat(off-topic): print the number of elements in tensors with llama-gguf
Branch: Mamba2SSD
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* style: valign
Branch: GGUFToolOutputs
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* Update examples/gguf/gguf.cpp
---------
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-11-05 19:58:16 +02:00
ed8aa63320
model-conversion : pass config to from_pretrained ( #16963 )
...
This commit modifies the script `run-org-model.py` to ensure that the
model configuration is explicitly passed to the `from_pretrained` method
when loading the model. It also removes a duplicate configuration
loading which was a mistake.
The motivation for this change is that enables the config object to be
modified and then passed to the model loading function, which can be
useful when testing new models.
2025-11-03 18:01:59 +01:00
e76554304d
lib: enable app optimization
2025-10-31 18:33:18 -07:00
33987b56fa
jni: introduce a logging util to filter different logging levels on different build types
2025-10-31 18:28:10 -07:00
3fa3c15c5c
lib: revert System.load back to System.loadLibrary
2025-10-31 13:54:41 -07:00
f94efbacbb
cleanup: remove Arm AI Chat/Playground app source code; replace with the basic sample app from https://github.com/hanyin-arm/Arm-AI-Chat-Sample
...
Note: the full Google Play version of AI Chat app will be open will be open sourced in another repo soon, therefore didn't go through the trouble of pruning the history using `git filter-repo` here.
2025-10-30 13:37:59 -07:00
cadaf8044b
lib: remove kleidi-llama related namings
2025-10-28 11:39:19 -07:00
266fc314ef
lib: change `LlamaTier` to `ArmCpuTier`
2025-10-28 11:39:19 -07:00
3644082a82
lib: perform engine state check inclusively instead of exclusively
2025-10-28 11:39:19 -07:00
f10d1ab022
lib: add File version for GGUF Magic number verification
2025-10-28 11:39:19 -07:00
f833c3a7ac
app: extract AppContent from MainActivity to a separate file in ui package
2025-10-28 11:39:19 -07:00
42e3972b30
app: remove deprecated SystemUIController from accompanist by migrating to EdgeToEdge
2025-10-28 11:39:19 -07:00
7c2e6d0a2f
app: bump ksp version
2025-10-28 11:39:19 -07:00
8897b78055
llama: update the app's package name and namespace
2025-10-28 11:39:19 -07:00
56e83b723b
llama: update the library's package name and namespace
2025-10-28 11:39:19 -07:00
96817ae667
llama: update the library name in JNI and CMake project
2025-10-28 11:39:19 -07:00
6dfdc2c105
lib: replace the factory pattern for deprecated tiered lib loading with single instance pattern
2025-10-28 11:39:19 -07:00
63e5bd0771
lib: support x86-64 by dynamically set Arm related definitions
2025-10-28 11:39:19 -07:00
8f90e42ee2
UI: fix the layout issue on large font sizes
2025-10-28 11:39:19 -07:00
930e707608
UI: better usage of tertiary colors to highlight model cards but not for warnings
2025-10-28 11:39:19 -07:00
ad85bca98b
UI: make more room for assistant message bubble's width
2025-10-28 11:39:19 -07:00
83abff8a64
UI: minor color palette changes; emphasize the bottom bar FABs; fix Settings Screen menu item label
2025-10-28 11:39:18 -07:00
2223c54cc6
core: further improve the performance on native methods
2025-10-28 11:39:18 -07:00
d5220549b6
UI: fix the font size auto scaling for ArmFeaturesVisualizer
2025-10-28 11:39:18 -07:00
480d774b0c
app: update adaptive + themed + legacy icons and app name
2025-10-28 11:39:18 -07:00
e0ddc37e2e
data: sort preselected models according to device's available RAM
2025-10-28 11:39:18 -07:00
687b86e924
core: organizing cmake arguments
2025-10-28 11:39:18 -07:00
6db4c70991
core: restructure Kleidi-Llama library
2025-10-28 11:39:18 -07:00
6cde2fe1bd
core: support GGML_CPU_ALL_VARIANTS on Android!
2025-10-28 11:39:18 -07:00
0c6ce7b9a3
UI: extract a reusable InfoAlertDialog
2025-10-28 11:39:18 -07:00
a4459b22d1
nit: append `®` to all `Arm` labels
2025-10-28 11:39:18 -07:00
5f06978945
nit: address Rojin's feedbacks on model import message again
2025-10-28 11:39:18 -07:00
eba09a3d40
UI: fix UI issues in the generic settings screen and navigation drawer
2025-10-28 11:39:18 -07:00
36c3768f52
data: make sure fetch preselected models in the same order of their IDs
2025-10-28 11:39:18 -07:00
2b70887725
UI: update Arm color palette from Philip.Watson3
2025-10-28 11:39:18 -07:00
8268d70518
UI: address Rojin's UX feedbacks - part 2
2025-10-28 11:39:18 -07:00
e067f7051b
UI: address Rojin's UX feedbacks
2025-10-28 11:39:18 -07:00
6fb4a94cc3
[WIP] UI: add Arm color palette from Philip.Watson3
2025-10-28 11:39:18 -07:00
d27933fffe
misc: use sentence case for CTA button labels
2025-10-28 11:39:18 -07:00
5471635c9d
UX: implement onboarding tooltips for model import and onboarding
2025-10-28 11:39:18 -07:00
1c73f6215f
UI: polish Hugging Face download dialog UI
2025-10-28 11:39:18 -07:00
58adb6c6a5
UI: update app name & about; polish top bars' indicators & buttons
2025-10-28 11:39:18 -07:00
b1bcb8126c
data: add hand crafted rules to filter the models fetched from HuggingFace API
2025-10-28 11:39:18 -07:00
f1269f4d39
UI: tracks user's first success on importing a model
2025-10-28 11:39:18 -07:00
c87ff9c1b3
UI: adds AppPreferences to track user onboarding status
2025-10-28 11:39:18 -07:00
a9b84b9db3
UI: add Tooltip on Import FAB for user onboarding
2025-10-28 11:39:18 -07:00
naco-siren
Georgi Gerganov
Gabe Goodhart
Daniel Bevenius
Han Yin