CI

feat: overriding quant types for specific tensors on model conversion #971

Sign in to view logs

Triggered via pull request July 7, 2025 13:11

wbruna

opened #724

wbruna:per_tensor_quant

Status Success

Total duration 42m 45s

Artifacts –

build.yml

on: pull_request

Matrix: windows-latest-cmake

ubuntu-latest-cmake

macOS-latest-cmake

Annotations

1 error and 2 warnings

windows-latest-cmake (avx512, -DGGML_NATIVE=OFF -DGGML_AVX512=ON -DGGML_AVX=ON -DGGML_AVX2=ON -DS...

Process completed with exit code 1.

windows-latest-cmake (cuda12, -DSD_CUDA=ON -DSD_BUILD_SHARED_LIBS=ON -DCMAKE_CUDA_ARCHITECTURES=9...

Failed to save: reserveCache failed: Cache service responded with 503

windows-latest-cmake (cuda12, -DSD_CUDA=ON -DSD_BUILD_SHARED_LIBS=ON -DCMAKE_CUDA_ARCHITECTURES=9...

Failed to restore: getCacheEntry failed: Cache service responded with 503