diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index 8a099ae75..48976020d 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -111,7 +111,7 @@ jobs:
           export UV_PYTHON=3.14
           echo "UV_PYTHON=3.14" >> "$GITHUB_ENV"
 
-          env_name="py314_release_source"
+          env_name="gptqmodel_py314_release_source"
           /opt/uv/setup_uv_venv.sh $env_name
 
       - name: Fetch PR by number
@@ -134,6 +134,12 @@ jobs:
           echo "PKG_NAME=$pkg" >> "$GITHUB_ENV"
           twine check "dist/$pkg"
 
+      - name: test installation
+        run: |
+          uv venv local_uv_env
+          source local_uv_env/bin/activate
+          uv pip install "dist/${{ env.PKG_NAME }}" torch
+
       - name: Upload to local
         continue-on-error: true
         run: |
diff --git a/.github/workflows/unit_tests.yml b/.github/workflows/unit_tests.yml
index 60638fbe8..d4f28cd0a 100644
--- a/.github/workflows/unit_tests.yml
+++ b/.github/workflows/unit_tests.yml
@@ -466,147 +466,46 @@ jobs:
         run: |
           rm -rf rm -rf ./* .[^.] .??*
 
-#  show-statistics:
-#    runs-on: [ self-hosted, xeon5 ]
-#    if: always() && inputs['exclusive-gpu'] && !cancelled()
-#    container:
-#      image: modelcloud/gptqmodel:alpine-ci-v1
-#    needs:
-#      - torch
-#    steps:
-#      - name: Print statistics
-#        run: curl "http://$RUNNER/gpu/get_vram_logs?id=${{ github.run_id }}"
-
-#  m4:
-#    runs-on: [ self-hosted, m4 ]
-#    needs:
-#      - check-vm
-#      - list-test-files
-#    if: false && (github.event.inputs.test_names == '' || contains(github.event.inputs.test_names, 'apple') || contains(github.event.inputs.test_names, 'mlx') )  && (needs.list-test-files.outputs.m4-files != '' && needs.list-test-files.outputs.m4-files != '[]') && !cancelled()
-#    strategy:
-#      fail-fast: false
-#      matrix:
-#        test_script: ${{ fromJSON(needs.list-test-files.outputs.m4-files) }}
-#    steps:
-#      - name: Print Env
-#        run: |
-#          echo "repo: ${{ env.repo }}"
-#          echo "ref: ${{ env.ref }}"
-#          ls -ahl .
-#
-#      - name: Checkout Codes
-#        uses: actions/checkout@v6
-#        with:
-#          repository: ${{ env.repo }}
-#          ref: ${{ env.ref }}
-#
-#      - name: Run test
-#        run: |
-#          export PATH="/opt/homebrew/bin:$PATH" && eval "$(pyenv init -)"
-#          rm -rf venv || true
-#
-#          echo "=== checking models dir is mounted"
-#          ls ../../../monster
-#
-#          echo "=== activating venv"
-#          pyenv global 3.11.11 && python -m venv venv
-#          source venv/bin/activate
-#
-#          rm profile.sb || true
-#
-#          curl -O http://$RUNNER/scripts/m4/profile.sb
-#
-#          echo "=== installing uv setuptools build"
-#          pip install setuptools build -U -i http://$RUNNER/simple --trusted-host $RUNNER --extra-index-url https://pypi.org/simple
-#
-#          echo "=== installing test tools"
-#          uv pip install pytest parameterized vllm device-smi mlx-lm -U -i http://$RUNNER/simple/ --trusted-host $RUNNER --extra-index-url https://pypi.org/simple
-#
-#          echo "=== installing gptqmodel"
-#          uv pip install . -i http://$RUNNER/simple/ --trusted-host $RUNNER --extra-index-url https://pypi.org/simple
-#
-#          echo "replacing model path"
-#          find tests -name "*.py" -exec sed -i '' 's/\/monster\/data\/model/..\/..\/..\/monster/g' {} +
-#
-#          TEST=${{ matrix.test_script }}
-#          if [[ ! "$TEST" == *.py ]]; then
-#          TEST="$TEST.py"
-#          fi
-#          echo "=== running test: $TEST"
-#          pytest tests/$TEST
-#
-#      - name: Clean cache
-#        if: always()
-#        run: |
-#          source venv/bin/activate && pip cache purge && uv cache clean || true
-#          rm -rf ../GPTQModel && mkdir ../GPTQModel
-#
-#  mac-test:
-#    runs-on: macos-latest
-#    env:
-#      CUDA_VISIBLE_DEVICES: ''
-#      TORCH_CUDA_ARCH_LIST: ''
-#      MAX_JOBS: 3
-#      BUILD_QQQ: 0
-#      BUILD_EORA: 0
-#      GPTQMODEL_BUILD_EXLLAMA_V1: 0
-#      GPTQMODEL_BUILD_EORA: 0
-#      GPTQMODEL_FORCE_BUILD: 0
-#    steps:
-#      - name: Checkout Codes
-#        uses: actions/checkout@v6
-#
-#      - uses: actions/setup-python@v6
-#        with:
-#          python-version: 3.12
-#          cache: 'pip'
-#
-##       it wastes too much time to find which exactly one caused installation failed, just unset them all.....
-#      - name: Install dependencies
-#        run: |
-#          unset CUDA_DEVICE_ORDER
-#          unset CUDA_VISIBLE_DEVICES
-#          unset TORCH_CUDA_ARCH_LIST
-#          unset PYTORCH_ALLOC_CONF
-#          unset MAX_JOBS
-#          unset RUNNER
-#          unset XEON5
-#          unset UV_INDEX_URL
-#          unset CUDA_VERSION
-#          unset TORCH_VERSION
-#          unset PYTHON_VERSION
-#          unset # PYTHON_GIL
-#          unset BUILD_QQQ
-#          unset BUILD_EORA
-#          unset GPTQMODEL_BUILD_EXLLAMA_V1
-#          unset GPTQMODEL_BUILD_EORA
-#          unset LEGACY_TESTS
-#          unset IGNORED_TEST_FILES
-#          unset GPTQMODEL_FORCE_BUILD
-#          unset repo
-#          unset ref
-#
-#          python -V
-#          python -m venv venv
-#          source venv/bin/activate
-#          pip install pip uv setuptools build wheel torch -U
-#          pip install meson-python -U
-#          pip install numpy==2.2.6 -U
-#
-#          uv pip install -e .
-#          pip install pip Pillow device_smi pypcre tokenicer threadpoolctl accelerate logbar transformers optimum torch -U
-#
-#      - name: Run test
-#        run: |
-#          source venv/bin/activate
-#          python - <<'PY'
-#          import os
-#          from transformers import pipeline
-#          os.environ["CUDA_VISIBLE_DEVICES"] = ""
-#          os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"
-#          llm_pipeline = pipeline(model="JunHowie/Qwen3-0.6B-GPTQ-Int4")
-#          output = llm_pipeline("Which city is the capital of France?", max_new_tokens=100)
-#          print(output)
-#
-#          assert "paris" in output.lower()
-#          PY
+  torch-test:
+    runs-on: [ self-hosted, xeon5 ]
+    container:
+      image: 10.0.13.31:5000/nvidia/cuda:130-ubuntu24.04_0325
+      options: --device /dev/dri --ipc=host --runtime=nvidia --gpus all
+      volumes:
+        - /monster/ci/env/entrypoint.sh:/entrypoint.sh
+        - /monster/ci/env/entrypoint.sh:/etc/profile.d/01-entrypoint.sh
+        - /dev/dri/by-path:/dev/dri/by-path
+        - /monster/ci/uv:/opt/uv
+        - /monster/ci/env:/opt/env
+    steps:
+      - name: Checkout Codes
+        uses: actions/checkout@v6
+        with:
+          repository: ${{ env.repo }}
+          ref: ${{ env.ref }}
+
+      - name: Test pypi pip
+        run: |
+          uv venv pypi_pip_env
+          source pypi_pip_env/bin/activate
+          uv pip install pip -U
+          pip install gptqmodel torch -U
+
+      - name: Test pypi uv
+        run: |
+          uv venv pypi_uv_env
+          source pypi_uv_env/bin/activate
+          uv pip install gptqmodel torch -U
+
+      - name: test local pip
+        run: |
+          uv venv local_pip_env
+          source local_pip_env/bin/activate
+          uv pip install pip -U
+          pip install . torch -U
+
+      - name: test local uv
+        run: |
+          uv venv local_uv_env
+          source local_uv_env/bin/activate
+          uv pip install . torch -U