add hf cache caching for GHA (#2247)

* add hf cache caching for GHA

* use modal volume to cache hf data

* make sure to update the cache as we add new fixtures in conftest
This commit is contained in:
Wing Lian
2025-01-09 15:59:54 -05:00
committed by GitHub
parent 7faf2b6e8e
commit 3c1921e400
4 changed files with 53 additions and 0 deletions

View File

@@ -61,6 +61,15 @@ jobs:
- name: Check out repository code
uses: actions/checkout@v4
- name: Restore HF cache
id: hf-cache-restore
uses: actions/cache/restore@v4
with:
path: |
/home/runner/.cache/huggingface/hub/datasets--*
/home/runner/.cache/huggingface/hub/models--*
key: ${{ runner.os }}-hf-hub-cache-${{ hashFiles('**/conftest.py') }}
- name: Setup Python
uses: actions/setup-python@v5
with:
@@ -101,6 +110,15 @@ jobs:
run: |
find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;
- name: Save HF cache
id: hf-cache
uses: actions/cache/save@v4
with:
path: |
/home/runner/.cache/huggingface/hub/datasets--*
/home/runner/.cache/huggingface/hub/models--*
key: ${{ steps.hf-cache-restore.outputs.cache-primary-key }}
pytest-sdist:
name: PyTest from Source Dist
runs-on: ubuntu-latest
@@ -116,6 +134,15 @@ jobs:
- name: Check out repository code
uses: actions/checkout@v4
- name: Restore HF cache
id: hf-cache-restore
uses: actions/cache/restore@v4
with:
path: |
/home/runner/.cache/huggingface/hub/datasets--*
/home/runner/.cache/huggingface/hub/models--*
key: ${{ runner.os }}-hf-hub-cache-${{ hashFiles('**/conftest.py') }}
- name: Setup Python
uses: actions/setup-python@v5
with:
@@ -157,6 +184,15 @@ jobs:
run: |
find "$(pip cache dir)/http-v2" -type f -mtime +14 -exec rm {} \;
- name: Save HF cache
id: hf-cache
uses: actions/cache/save@v4
with:
path: |
/home/runner/.cache/huggingface/hub/datasets--*
/home/runner/.cache/huggingface/hub/models--*
key: ${{ steps.hf-cache-restore.outputs.cache-primary-key }}
docker-e2e-tests-1st:
if: ${{ ! contains(github.event.commits[0].message, '[skip e2e]') && github.repository_owner == 'axolotl-ai-cloud' }}
# this job needs to be run on self-hosted GPU runners...