fix: update the comment format and update github actions

.github/workflows/build.yml

@@ -1,29 +1,42 @@
 name: GitHub Actions Demo
 run-name: Pushed by ${{ github.actor }} 🚀
-on: [push]
+on: [push, pull_request_target]
 jobs:
-  test-xfuser:
-    name: Test xfuser
+  upload:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Run a multi-line script
+      run: git archive --format zip HEAD > xDiT.zip
+    - name: copy file via ssh password
+      uses: appleboy/[email protected]
+      with:
+        host: ${{ secrets.SSH_HOST }}
+        port: ${{ secrets.SSH_PORT }}
+        username: ${{ secrets.SSH_USER }}
+        password: ${{ secrets.SSH_KEY }}
+        source: "xDiT.zip"
+        target: "~/"
+  setup-env-and-test:
+    needs: upload
     runs-on: [self-hosted, linux, x64]
-    strategy:
-      fail-fast: false
-      max-parallel: 5
-      matrix:
-        python-versions: [3.11]
-        torch-versions: [2.4.1]
-        include:
-          - python-versions: 3.11
-            python-versions-full: 3_11
-          - torch-versions: 2.4.1
-            torch-versions-full: 2_4_1
+    continue-on-error: true
     steps:
-      - uses: actions/checkout@v4
-
+      - name: unzip
+        run: rm -rf ~/xDiT
+      - run: mkdir ~/xDiT
+      - run: unzip ~/xDiT.zip -d ~/xDiT
       - name: Setup docker
-        run: docker run --rm --name xfuser_test_docker -d -i -t --runtime=nvidia --gpus all -v ~/actions-runner/_work/xDiT/xDiT:/code xfuser_cicd/test-py_${{matrix.python-versions-full}}-torch_${{matrix.torch-versions-full}} /bin/bash
+        run: docker run --rm --name xfuser_test_docker -d -i -t --runtime=nvidia --gpus all -v /cfs:/cfs -v /mnt:/mnt -v ~/xDiT:/code xfuser_cicd/test-py_3_11-torch_2_4_1 /bin/bash
       - name: Install xfuser
-        run: docker exec -w /code xfuser_test_docker pip${{matrix.python-versions}} install -e .
+        run: docker exec -w /code xfuser_test_docker pip3.11 install -e .
       - name: Test xfuser
         run: docker exec -w /code xfuser_test_docker sh -c "torchrun --nproc_per_node=8 ./examples/sd3_example.py --model /cfs/dit/stable-diffusion-3-medium-diffusers --pipefusion_parallel_degree 2 --ulysses_degree 2 --ring_degree 1 --height 1024 --width 1024 --no_use_resolution_binning --num_inference_steps 20 --warmup_steps 0 --prompt 'A small dog' --use_cfg_parallel"
+  clear-env:
+    needs: setup-env-and-test
+    runs-on: [self-hosted, linux, x64]
+    steps:
+      - name: Remove Files
+        run: docker exec -w /code xfuser_test_docker sh -c "rm -r *"
       - name: Destroy docker
         run: docker stop xfuser_test_docker

xfuser/model_executor/layers/attention_processor.py

@@ -121,23 +121,23 @@ def __init__(
         assert (to_k.bias is None) == (to_v.bias is None)
         assert to_k.weight.shape == to_v.weight.shape
 
-        '''in_size, out_size = to_k.in_features, to_k.out_features
-        to_kv = nn.Linear(
-            in_size,
-            out_size * 2,
-            bias=to_k.bias is not None,
-            device=to_k.weight.device,
-            dtype=to_k.weight.dtype,
-        )
-        to_kv.weight.data[:out_size].copy_(to_k.weight.data)
-        to_kv.weight.data[out_size:].copy_(to_v.weight.data)
+        # in_size, out_size = to_k.in_features, to_k.out_features
+        # to_kv = nn.Linear(
+        #     in_size,
+        #     out_size * 2,
+        #     bias=to_k.bias is not None,
+        #     device=to_k.weight.device,
+        #     dtype=to_k.weight.dtype,
+        # )
+        # to_kv.weight.data[:out_size].copy_(to_k.weight.data)
+        # to_kv.weight.data[out_size:].copy_(to_v.weight.data)
 
-        if to_k.bias is not None:
-            assert to_v.bias is not None
-            to_kv.bias.data[:out_size].copy_(to_k.bias.data)
-            to_kv.bias.data[out_size:].copy_(to_v.bias.data)
+        # if to_k.bias is not None:
+        #     assert to_v.bias is not None
+        #     to_kv.bias.data[:out_size].copy_(to_k.bias.data)
+        #     to_kv.bias.data[out_size:].copy_(to_v.bias.data)
 
-        self.to_kv = to_kv'''
+        # self.to_kv = to_kv
 
 
 class xFuserAttentionProcessorRegister: