Fix nightly torch CI (#40469)
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
22
.github/workflows/self-nightly-caller.yml
vendored
22
.github/workflows/self-nightly-caller.yml
vendored
@@ -12,12 +12,34 @@ on:
|
|||||||
branches:
|
branches:
|
||||||
- run_ci_with_nightly_torch*
|
- run_ci_with_nightly_torch*
|
||||||
|
|
||||||
|
# Used for `push` to easily modify the target workflow runs to compare against
|
||||||
|
env:
|
||||||
|
prev_workflow_run_id: ""
|
||||||
|
other_workflow_run_id: ""
|
||||||
|
|
||||||
|
|
||||||
jobs:
|
jobs:
|
||||||
build_nightly_torch_ci_images:
|
build_nightly_torch_ci_images:
|
||||||
name: Build CI Docker Images with nightly torch
|
name: Build CI Docker Images with nightly torch
|
||||||
uses: ./.github/workflows/build-nightly-ci-docker-images.yml
|
uses: ./.github/workflows/build-nightly-ci-docker-images.yml
|
||||||
secrets: inherit
|
secrets: inherit
|
||||||
|
|
||||||
|
setup:
|
||||||
|
name: Setup
|
||||||
|
runs-on: ubuntu-22.04
|
||||||
|
steps:
|
||||||
|
- name: Setup
|
||||||
|
run: |
|
||||||
|
mkdir "setup_values"
|
||||||
|
echo "${{ inputs.prev_workflow_run_id || env.prev_workflow_run_id }}" > "setup_values/prev_workflow_run_id.txt"
|
||||||
|
echo "${{ inputs.other_workflow_run_id || env.other_workflow_run_id }}" > "setup_values/other_workflow_run_id.txt"
|
||||||
|
|
||||||
|
- name: Upload artifacts
|
||||||
|
uses: actions/upload-artifact@v4
|
||||||
|
with:
|
||||||
|
name: setup_values
|
||||||
|
path: setup_values
|
||||||
|
|
||||||
model-ci:
|
model-ci:
|
||||||
name: Model CI
|
name: Model CI
|
||||||
needs: build_nightly_torch_ci_images
|
needs: build_nightly_torch_ci_images
|
||||||
|
|||||||
@@ -32,7 +32,10 @@ RUN python3 -m pip uninstall -y flax jax
|
|||||||
|
|
||||||
RUN python3 -m pip install --no-cache-dir -U timm
|
RUN python3 -m pip install --no-cache-dir -U timm
|
||||||
|
|
||||||
RUN python3 -m pip install --no-cache-dir git+https://github.com/facebookresearch/detectron2.git pytesseract
|
RUN [ "$PYTORCH" != "pre" ] && python3 -m pip install --no-cache-dir git+https://github.com/facebookresearch/detectron2.git || echo "Don't install detectron2 with nightly torch"
|
||||||
|
|
||||||
|
RUN python3 -m pip install --no-cache-dir pytesseract
|
||||||
|
|
||||||
RUN python3 -m pip install -U "itsdangerous<2.1.0"
|
RUN python3 -m pip install -U "itsdangerous<2.1.0"
|
||||||
|
|
||||||
RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/accelerate@main#egg=accelerate
|
RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/accelerate@main#egg=accelerate
|
||||||
@@ -52,7 +55,7 @@ RUN python3 -m pip install --no-cache-dir bitsandbytes
|
|||||||
RUN python3 -m pip install --no-cache-dir quanto
|
RUN python3 -m pip install --no-cache-dir quanto
|
||||||
|
|
||||||
# After using A10 as CI runner, let's run FA2 tests
|
# After using A10 as CI runner, let's run FA2 tests
|
||||||
RUN python3 -m pip uninstall -y ninja && python3 -m pip install --no-cache-dir ninja && python3 -m pip install flash-attn --no-cache-dir --no-build-isolation
|
RUN [ "$PYTORCH" != "pre" ] && python3 -m pip uninstall -y ninja && python3 -m pip install --no-cache-dir ninja && python3 -m pip install flash-attn --no-cache-dir --no-build-isolation || echo "Don't install FA2 with nightly torch"
|
||||||
|
|
||||||
# TODO (ydshieh): check this again
|
# TODO (ydshieh): check this again
|
||||||
# `quanto` will install `ninja` which leads to many `CUDA error: an illegal memory access ...` in some model tests
|
# `quanto` will install `ninja` which leads to many `CUDA error: an illegal memory access ...` in some model tests
|
||||||
|
|||||||
Reference in New Issue
Block a user