vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml-quants : provide ggml_vqtbl1q_u8 for 64bit compatibility (#5711)

Browse source 
* [ggml-quants] Provide ggml_vqtbl1q_u8 for 64bit compatibility

vqtbl1q_u8 is not part of arm v7 neon library

* [android-example] Remove abi filter after arm v7a fix

* [github-workflows] Do not skip Android armeabi-v7a build
This commit is contained in:
Radosław Gryta 2024-02-25 19:43:00 +01:00 • committed by GitHub
parent f1a98c5254
commit abbabc5e51
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 32 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

3
.github/workflows/build.yml vendored
View file

@ -669,8 +669,7 @@ jobs:
run: |
cd examples/llama.android
# Skip armeabi-v7a for now (https://github.com/llvm/llvm-project/issues/65820).
./gradlew build --no-daemon -Pskip-armeabi-v7a
./gradlew build --no-daemon
# freeBSD-latest:
# runs-on: macos-12