525fc55cef
- 修复 FineTuneCreateView GPU 选择使用 v-for idx 替代真实 gpu.id 导致 多节点环境下 GPU 索引错误（如 gpu-node-02 仅 GPU 0 但请求 GPU 1） - GPU 选择改为单选模式，已离线节点自动过滤不展示 - GPU 卡片增加节点编号展示 - 修复 CUDA_VISIBLE_DEVICES=all 无效值导致 torch.cuda.is_available() False 改为 CUDA_VISIBLE_DEVICES=0 - .gitignore 新增 .claude/ CLAUDE.md 排除规则 - GpuInfo 类型增加 node_id/node_code/node_name 字段 Co-Authored-By: Claude <noreply@anthropic.com>
41 lines
1.3 KiB
Bash
41 lines
1.3 KiB
Bash
COMPUTE_ENV=prod
|
|
COMPUTE_HOST_ID=gpu-node-01
|
|
COMPUTE_EXECUTION_MODE=real
|
|
MODELTF_ROUTE_PREFIX=/modelTF
|
|
# Five-digit host ports exposed outside the compute server.
|
|
COMPUTE_API_PORT=19100
|
|
FILE_GATEWAY_PORT=19101
|
|
COMPUTE_API_IMAGE=yg-ft-compute-api:latest
|
|
|
|
# The application server actively polls Compute API; compute server does not need reverse access.
|
|
COMPUTE_AUTH_ENABLED=true
|
|
COMPUTE_SERVICE_TOKEN=change_me
|
|
ENABLE_APP_CALLBACK=false
|
|
|
|
# LLaMA-Factory is provided by the official hiyouga/llamafactory base image.
|
|
LLAMA_FACTORY_HOME=/app/LLaMA-Factory
|
|
|
|
YG_FT_DATA_ROOT=/data/yg-ft
|
|
YG_FT_DATA_ROOT_HOST=./data/yg-ft
|
|
YG_FT_MODEL_ROOT=/data/yg-ft/models
|
|
YG_FT_MODEL_ROOT_HOST=./data/yg-ft/models
|
|
YG_FT_DATASET_ROOT=/data/yg-ft/datasets
|
|
YG_FT_DATASET_ROOT_HOST=./data/yg-ft/datasets
|
|
YG_FT_OUTPUT_ROOT=/data/yg-ft/outputs
|
|
YG_FT_OUTPUT_ROOT_HOST=./data/yg-ft/outputs
|
|
TRAINING_LOG_ROOT=/opt/yg-ft/logs/training
|
|
TRAINING_LOG_ROOT_HOST=./data/yg-ft/logs/training
|
|
COMPUTE_LOG_ROOT_HOST=./data/yg-ft/logs/compute
|
|
|
|
# Optional fallback used when nvidia-smi is unavailable.
|
|
# Leave COMPUTE_GPU_COUNT=0 on real GPU servers with working NVIDIA runtime.
|
|
COMPUTE_GPU_COUNT=0
|
|
COMPUTE_GPU_NAME=NVIDIA A800-SXM4-80GB
|
|
COMPUTE_GPU_MEMORY_GB=80
|
|
COMPUTE_GPU_POWER_LIMIT_W=300
|
|
|
|
LOG_DIR=/opt/yg-ft/logs/compute
|
|
CUDA_VISIBLE_DEVICES=0
|
|
NVIDIA_VISIBLE_DEVICES=all
|
|
NVIDIA_DRIVER_CAPABILITIES=compute,utility
|