LLM inference in C/C++
C++ ggml
ci : make cache bucket public (#27728)
Sigbjørn Skjæretda9b5d68c31b
diff --git a/.github/actions/ccache-buckets/action.yml b/.github/actions/ccache-buckets/action.ymlindex 8eb65d275c..eaa8d164eb 100644--- a/.github/actions/ccache-buckets/action.yml+++ b/.github/actions/ccache-buckets/action.yml@@ -58,34 +58,38 @@ runs:if: ${{ inputs.save == 'true' }}shell: bashrun: |- set +e -uo pipefail- source .venv-hf/bin/activate- CCACHE_DIR=$(ccache -k cache_dir)- if [[ -d "$CCACHE_DIR" ]]; then- ccache -s- if [[ -n "${{ inputs.evict-old-files }}" ]]; then- ccache --evict-older-than "${{ inputs.evict-old-files }}"- fi- DATESTAMP=$(date -u +'%Y-%m-%dT%H:%M:%SZ')- CACHEFILE="${{ inputs.key }}-$DATESTAMP.tar.gz"- if tar -czf ccache_bucket.tar.gz -C "$CCACHE_DIR" .; then- hf buckets cp ccache_bucket.tar.gz "hf://buckets/${{ inputs.hf_bucket }}/${{ inputs.folder }}/$CACHEFILE"+ if [[ -n "$HF_TOKEN" ]]; then+ set +e -uo pipefail+ source .venv-hf/bin/activate+ CCACHE_DIR=$(ccache -k cache_dir)+ if [[ -d "$CCACHE_DIR" ]]; then+ ccache -s+ if [[ -n "${{ inputs.evict-old-files }}" ]]; then+ ccache --evict-older-than "${{ inputs.evict-old-files }}"+ fi+ DATESTAMP=$(date -u +'%Y-%m-%dT%H:%M:%SZ')+ CACHEFILE="${{ inputs.key }}-$DATESTAMP.tar.gz"+ if tar -czf ccache_bucket.tar.gz -C "$CCACHE_DIR" .; then+ hf buckets cp ccache_bucket.tar.gz "hf://buckets/${{ inputs.hf_bucket }}/${{ inputs.folder }}/$CACHEFILE"+ fi+ rm ccache_bucket.tar.gz+ else+ echo "'$CCACHE_DIR' not found."fi- rm ccache_bucket.tar.gz- else- echo "'$CCACHE_DIR' not found."fi- name: Remove old ccache files from bucketsif: ${{ inputs.save == 'true' }}shell: bashrun: |- set +e -uo pipefail- source .venv-hf/bin/activate- CACHE_FILES=$(hf buckets list "hf://buckets/${{ inputs.hf_bucket }}/${{ inputs.folder }}" --json | jq -r '[.[] | select(.type == "file") | select((.uploaded_at | .[:19]+"Z" | fromdateiso8601) < (now - 5 * 60)) | select(.path | startswith("${{ inputs.folder }}/${{ inputs.key }}") and endswith(".tar.gz"))] | sort_by(.path)[:-1] | .[] | [.path // ""] | @tsv')- if [[ -n "$CACHE_FILES" ]]; then- echo "Removing old ccache files..."- while IFS=$'\t' read -r CACHE_PATH; do- hf buckets rm "hf://buckets/${{ inputs.hf_bucket }}/$CACHE_PATH" -y- done <<< "$CACHE_FILES"+ if [[ -n "$HF_TOKEN" ]]; then+ set +e -uo pipefail+ source .venv-hf/bin/activate+ CACHE_FILES=$(hf buckets list "hf://buckets/${{ inputs.hf_bucket }}/${{ inputs.folder }}" --json | jq -r '[.[] | select(.type == "file") | select((.uploaded_at | .[:19]+"Z" | fromdateiso8601) < (now - 5 * 60)) | select(.path | startswith("${{ inputs.folder }}/${{ inputs.key }}") and endswith(".tar.gz"))] | sort_by(.path)[:-1] | .[] | [.path // ""] | @tsv')+ if [[ -n "$CACHE_FILES" ]]; then+ echo "Removing old ccache files..."+ while IFS=$'\t' read -r CACHE_PATH; do+ hf buckets rm "hf://buckets/${{ inputs.hf_bucket }}/$CACHE_PATH" -y+ done <<< "$CACHE_FILES"+ fifidiff --git a/.github/workflows/build-cuda-ubuntu.yml b/.github/workflows/build-cuda-ubuntu.ymlindex 215299670a..80bd782095 100644--- a/.github/workflows/build-cuda-ubuntu.yml+++ b/.github/workflows/build-cuda-ubuntu.yml@@ -65,7 +65,7 @@ jobs:with:key: cuda-ubuntu-24.04-cudafolder: llama.cpp- hf_bucket: ${{ vars.HF_BUCKET_CACHE_OUTPUT }}+ hf_bucket: ggml-org/cache- name: Build with CMake# TODO: Remove GGML_CUDA_CUB_3DOT2 flag once CCCL 3.2 is bundled within CTK and that CTK version is used in this project@@ -89,7 +89,7 @@ jobs:key: cuda-ubuntu-24.04-cudafolder: llama.cppevict-old-files: 1d- hf_bucket: ${{ vars.HF_BUCKET_CACHE_OUTPUT }}+ hf_bucket: ggml-org/cachesave: truehip:@@ -120,7 +120,7 @@ jobs:with:key: cuda-ubuntu-22.04-hipfolder: llama.cpp- hf_bucket: ${{ vars.HF_BUCKET_CACHE_OUTPUT }}+ hf_bucket: ggml-org/cache- name: Build with native CMake HIP supportid: cmake_build@@ -140,7 +140,7 @@ jobs:key: cuda-ubuntu-22.04-hipfolder: llama.cppevict-old-files: 1d- hf_bucket: ${{ vars.HF_BUCKET_CACHE_OUTPUT }}+ hf_bucket: ggml-org/cachesave: truemusa:@@ -171,7 +171,7 @@ jobs:with:key: cuda-ubuntu-22.04-musafolder: llama.cpp- hf_bucket: ${{ vars.HF_BUCKET_CACHE_OUTPUT }}+ hf_bucket: ggml-org/cache- name: Build with native CMake MUSA supportid: cmake_build@@ -189,5 +189,5 @@ jobs:key: cuda-ubuntu-22.04-musafolder: llama.cppevict-old-files: 1d- hf_bucket: ${{ vars.HF_BUCKET_CACHE_OUTPUT }}+ hf_bucket: ggml-org/cachesave: true