Merge pull request #4970 from HardAndHeavy/add-rocm

Add ROCm support
This commit is contained in:
hoshi-hiyouga 2024-07-26 11:41:23 +08:00 committed by GitHub
commit b8896b9b8b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 128 additions and 4 deletions

2
.gitignore vendored
View File

@ -160,6 +160,8 @@ cython_debug/
.idea/
# custom .gitignore
ms_cache/
hf_cache/
cache/
config/
saves/

View File

@ -425,16 +425,24 @@ For CUDA users:
```bash
cd docker/docker-cuda/
docker-compose up -d
docker-compose exec llamafactory bash
docker compose up -d
docker compose exec llamafactory bash
```
For Ascend NPU users:
```bash
cd docker/docker-npu/
docker-compose up -d
docker-compose exec llamafactory bash
docker compose up -d
docker compose exec llamafactory bash
```
For ROCm users:
```bash
cd docker/docker-rocm/
docker compose up -d
docker compose exec llamafactory bash
```
<details><summary>Build without Docker Compose</summary>
@ -496,6 +504,34 @@ docker run -dit \
docker exec -it llamafactory bash
```
For ROCm users:
```bash
docker build -f ./docker/docker-rocm/Dockerfile \
--build-arg INSTALL_BNB=false \
--build-arg INSTALL_VLLM=false \
--build-arg INSTALL_DEEPSPEED=false \
--build-arg INSTALL_FLASHATTN=false \
--build-arg PIP_INDEX=https://pypi.org/simple \
-t llamafactory:latest .
docker run -dit \
-v ./hf_cache:/root/.cache/huggingface \
-v ./ms_cache:/root/.cache/modelscope \
-v ./data:/app/data \
-v ./output:/app/output \
-v ./saves:/app/saves \
-p 7860:7860 \
-p 8000:8000 \
--device=/dev/kfd \
--device=/dev/dri \
--shm-size 16G \
--name llamafactory \
llamafactory:latest
docker exec -it llamafactory bash
```
</details>
<details><summary>Details about volume</summary>

View File

@ -0,0 +1,57 @@
FROM hardandheavy/transformers-rocm:2.1.0
# 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 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; \
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

View File

@ -0,0 +1,29 @@
services:
llamafactory:
build:
dockerfile: ./docker/docker-rocm/Dockerfile
context: ../..
args:
INSTALL_BNB: false
INSTALL_VLLM: false
INSTALL_DEEPSPEED: false
INSTALL_FLASHATTN: false
PIP_INDEX: https://pypi.org/simple
container_name: llamafactory
volumes:
- ../../hf_cache:/root/.cache/huggingface
- ../../ms_cache:/root/.cache/modelscope
- ../../data:/app/data
- ../../output:/app/output
- ../../saves:/app/saves
ports:
- "7860:7860"
- "8000:8000"
ipc: host
tty: true
stdin_open: true
command: bash
devices:
- /dev/kfd:/dev/kfd
- /dev/dri:/dev/dri
restart: unless-stopped