test llama_factory

2024-12-29 10:25:38 +00:00
parent fd4d12d88c
commit 5b5fcda5e5
263 changed files with 88555 additions and 0 deletions
@@ -0,0 +1,72 @@
+# Default use the NVIDIA official image with PyTorch 2.3.0
+# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/index.html
+ARG BASE_IMAGE=nvcr.io/nvidia/pytorch:24.02-py3
+FROM ${BASE_IMAGE}
+
+# Define environments
+ENV MAX_JOBS=4
+ENV FLASH_ATTENTION_FORCE_BUILD=TRUE
+ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
+
+# Define installation arguments
+ARG INSTALL_BNB=false
+ARG INSTALL_VLLM=false
+ARG INSTALL_DEEPSPEED=false
+ARG INSTALL_FLASHATTN=false
+ARG INSTALL_LIGER_KERNEL=false
+ARG INSTALL_HQQ=false
+ARG INSTALL_EETQ=false
+ARG PIP_INDEX=https://pypi.org/simple
+
+# Set the working directory
+WORKDIR /app
+
+# Install the requirements
+COPY requirements.txt /app
+RUN pip config set global.index-url "$PIP_INDEX" && \
+    pip config set global.extra-index-url "$PIP_INDEX" && \
+    python -m pip install --upgrade pip && \
+    python -m pip install -r requirements.txt
+
+# Copy the rest of the application into the image
+COPY . /app
+
+# Install the LLaMA Factory
+RUN EXTRA_PACKAGES="metrics"; \
+    if [ "$INSTALL_BNB" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},bitsandbytes"; \
+    fi; \
+    if [ "$INSTALL_VLLM" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},vllm"; \
+    fi; \
+    if [ "$INSTALL_DEEPSPEED" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
+    fi; \
+    if [ "$INSTALL_LIGER_KERNEL" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},liger-kernel"; \
+    fi; \
+    if [ "$INSTALL_HQQ" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},hqq"; \
+    fi; \
+    if [ "$INSTALL_EETQ" == "true" ]; then \
+        EXTRA_PACKAGES="${EXTRA_PACKAGES},eetq"; \
+    fi; \
+    pip install -e ".[$EXTRA_PACKAGES]"
+
+# Rebuild flash attention
+RUN pip uninstall -y transformer-engine flash-attn && \
+    if [ "$INSTALL_FLASHATTN" == "true" ]; then \
+        pip uninstall -y ninja && pip install ninja && \
+        pip install --no-cache-dir flash-attn --no-build-isolation; \
+    fi
+
+# Set up volumes
+VOLUME [ "/root/.cache/huggingface", "/root/.cache/modelscope", "/app/data", "/app/output" ]
+
+# Expose port 7860 for the LLaMA Board
+ENV GRADIO_SERVER_PORT 7860
+EXPOSE 7860
+
+# Expose port 8000 for the API service
+ENV API_PORT 8000
+EXPOSE 8000
@@ -0,0 +1,37 @@
+services:
+  llamafactory:
+    build:
+      dockerfile: ./docker/docker-cuda/Dockerfile
+      context: ../..
+      args:
+        INSTALL_BNB: false
+        INSTALL_VLLM: false
+        INSTALL_DEEPSPEED: false
+        INSTALL_FLASHATTN: false
+        INSTALL_LIGER_KERNEL: false
+        INSTALL_HQQ: false
+        INSTALL_EETQ: false
+        PIP_INDEX: https://pypi.org/simple
+    container_name: llamafactory
+    volumes:
+      - ../../hf_cache:/root/.cache/huggingface
+      - ../../ms_cache:/root/.cache/modelscope
+      - ../../om_cache:/root/.cache/openmind
+      - ../../data:/app/data
+      - ../../output:/app/output
+    ports:
+      - "7860:7860"
+      - "8000:8000"
+    ipc: host
+    tty: true
+    shm_size: '16gb'
+    stdin_open: true
+    command: bash
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            count: "all"
+            capabilities: [gpu]
+    restart: unless-stopped