Merge remote-tracking branch 'refs/remotes/origin/main'

.github/workflows/auto-release.yml

@@ -0,0 +1,28 @@
+name: Weekly Snapshot Release
+on:
+  schedule:
+    - cron: '15 20 * * 0'
+  workflow_dispatch: {}
+
+jobs:
+  create_release:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+
+      - name: Set snapshot tag
+        id: set_snapshot_tag
+        run: echo ::set-output name=tag::snapshot-$(date +'%Y-%m-%d')
+
+      - name: Create release
+        id: create_release
+        uses: softprops/action-gh-release@v1
+        with:
+          generate_release_notes: true
+          tag_name: ${{ steps.set_snapshot_tag.outputs.tag }}
+          name: ${{ steps.set_snapshot_tag.outputs.tag }}
+          draft: false
+          prerelease: false
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

docker/Dockerfile

@@ -11,8 +11,8 @@ WORKDIR /build
 RUN --mount=type=cache,target=/root/.cache/pip,rw \
     python3 -m venv /build/venv && \
     . /build/venv/bin/activate && \
-    pip3 install --upgrade pip setuptools wheel && \
-    pip3 install torch torchvision torchaudio && \
+    pip3 install --upgrade pip setuptools wheel ninja && \
+    pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 && \
     pip3 install -r requirements.txt
 
 # https://developer.nvidia.com/cuda-gpus
@@ -31,6 +31,7 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked,rw apt-get update &&
     rm -rf /var/lib/apt/lists/*
 
 RUN --mount=type=cache,target=/root/.cache/pip,rw pip3 install virtualenv
+
 RUN mkdir /app
 
 WORKDIR /app
@@ -42,8 +43,9 @@ RUN test -n "${WEBUI_VERSION}" && git reset --hard ${WEBUI_VERSION} || echo "Usi
 RUN virtualenv /app/venv
 RUN --mount=type=cache,target=/root/.cache/pip,rw \
     . /app/venv/bin/activate && \
-    pip3 install --upgrade pip setuptools wheel && \
-    pip3 install torch torchvision torchaudio sentence_transformers xformers
+    pip3 install --upgrade pip setuptools wheel ninja && \
+    pip3 install torch --index-url https://download.pytorch.org/whl/cu118 && \
+    pip3 install torchvision torchaudio sentence_transformers xformers
 
 # Copy and install GPTQ-for-LLaMa
 COPY --from=builder /build /app/repositories/GPTQ-for-LLaMa

requirements.txt

@@ -5,7 +5,7 @@ einops
 exllamav2==0.0.6; platform_system != "Darwin" and platform_machine != "x86_64"
 gradio==3.47.*
 markdown
-numpy==1.24
+numpy==1.24.*
 optimum==1.13.1
 pandas
 peft==0.5.*

requirements_amd.txt

@@ -5,7 +5,7 @@ einops
 exllamav2==0.0.6
 gradio==3.47.*
 markdown
-numpy==1.24
+numpy==1.24.*
 optimum==1.13.1
 pandas
 peft==0.5.*

requirements_amd_noavx2.txt

@@ -5,7 +5,7 @@ einops
 exllamav2==0.0.6
 gradio==3.47.*
 markdown
-numpy==1.24
+numpy==1.24.*
 optimum==1.13.1
 pandas
 peft==0.5.*

requirements_apple_intel.txt

@@ -5,7 +5,7 @@ einops
 exllamav2==0.0.6
 gradio==3.47.*
 markdown
-numpy==1.24
+numpy==1.24.*
 optimum==1.13.1
 pandas
 peft==0.5.*

requirements_apple_silicon.txt

@@ -5,7 +5,7 @@ einops
 exllamav2==0.0.6
 gradio==3.47.*
 markdown
-numpy==1.24
+numpy==1.24.*
 optimum==1.13.1
 pandas
 peft==0.5.*

requirements_cpu_only.txt

@@ -5,7 +5,7 @@ einops
 exllamav2==0.0.6
 gradio==3.47.*
 markdown
-numpy==1.24
+numpy==1.24.*
 optimum==1.13.1
 pandas
 peft==0.5.*

requirements_cpu_only_noavx2.txt

@@ -5,7 +5,7 @@ einops
 exllamav2==0.0.6
 gradio==3.47.*
 markdown
-numpy==1.24
+numpy==1.24.*
 optimum==1.13.1
 pandas
 peft==0.5.*

requirements_noavx2.txt

@@ -5,7 +5,7 @@ einops
 exllamav2==0.0.6; platform_system != "Darwin" and platform_machine != "x86_64"
 gradio==3.47.*
 markdown
-numpy==1.24
+numpy==1.24.*
 optimum==1.13.1
 pandas
 peft==0.5.*

requirements_nowheels.txt

@@ -5,7 +5,7 @@ einops
 exllamav2==0.0.6
 gradio==3.47.*
 markdown
-numpy==1.24
+numpy==1.24.*
 optimum==1.13.1
 pandas
 peft==0.5.*