From ff8b88a948fc2f6aba421ca64ad165291928dcee Mon Sep 17 00:00:00 2001
From: Yih-Dar <2521628+ydshieh@users.noreply.github.com>
Date: Tue, 26 Aug 2025 22:02:15 +0200
Subject: [PATCH] Fix nightly torch CI (#40469)

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
---
 .github/workflows/self-nightly-caller.yml     | 22 +++++++++++++++++++
 docker/transformers-all-latest-gpu/Dockerfile |  7 ++++--
 2 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/self-nightly-caller.yml b/.github/workflows/self-nightly-caller.yml
index 6192c8039f..48edaf8187 100644
--- a/.github/workflows/self-nightly-caller.yml
+++ b/.github/workflows/self-nightly-caller.yml
@@ -12,12 +12,34 @@ on:
     branches:
       - 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:
   build_nightly_torch_ci_images:
     name: Build CI Docker Images with nightly torch
     uses: ./.github/workflows/build-nightly-ci-docker-images.yml
     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:
     name: Model CI
     needs: build_nightly_torch_ci_images
diff --git a/docker/transformers-all-latest-gpu/Dockerfile b/docker/transformers-all-latest-gpu/Dockerfile
index 1f1cabe356..66aef6578f 100644
--- a/docker/transformers-all-latest-gpu/Dockerfile
+++ b/docker/transformers-all-latest-gpu/Dockerfile
@@ -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 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 --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
 
 # 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
 # `quanto` will install `ninja` which leads to many `CUDA error: an illegal memory access ...` in some model tests