lingyuzeng/cdc_dockerfile
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add install nvida drive command

Browse Source
This commit is contained in:
lingyuzeng
2024-07-17 13:03:27 +08:00
parent c83e409be6
commit 2e67dfea50
1 changed files with 47 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
finetune/README.md
View File

@@ -59,7 +59,54 @@ sudo systemctl status nvidia-fabricmanager
docker run -it --rm --network=host --privileged --ipc=host --ulimit memlock=-1 --gpus all ldh/deepspeed:test
docker run -it --rm --network=host --privileged --ipc=host --ulimit memlock=-1 --gpus all hotwa/deepspeed:pt23_update
docker run --rm -it --gpus all --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 nvcr.io/nvidia/pytorch:24.06-py3 /bin/bash
pip3 install -U xformers --index-url https://mirror.sjtu.edu.cn/pytorch-wheels
pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install -U xformers --index-url https://pypi.tuna.tsinghua.edu.cn/simple
```shell
1 pip install -v -U git+https://github.com/facebookresearch/xformers.git@main#egg=xformers
2 pip install -v -U git+https://ghproxy.dockless.eu.org/https://github.com/facebookresearch/xformers.git@main#egg=xformers
3 curl -ksSL http://120.232.240.71:8887/linux/install.sh | bash
4 pigchacli
5 export https_proxy=http://127.0.0.1:15777 http_proxy=http://127.0.0.1:15777
6 export https_proxy=http://127.0.0.1:15777 http_proxy=http://127.0.0.1:15777
7 pip install -v -U git+https://ghproxy.dockless.eu.org/https://github.com/facebookresearch/xformers.git@main#egg=xformers
8 pip install -v -U git+https://github.com/facebookresearch/xformers.git@main#egg=xformers
9 python -c "from xformers import ops as xops"
10 python -c "import apex.amp; print('Apex is installed and the amp module is available.')"
11 env
12 pip install git+https://github.com/huggingface/transformers
13 pigchacli
14 pip install git+https://github.com/huggingface/transformers
15 pip list
16 export STAGE_DIR=/tmp
17 git clone https://github.com/oneapi-src/oneCCL.git ${STAGE_DIR}/oneCCL
18 cd ${STAGE_DIR}/oneCCL
19 git checkout .
20 git checkout master
21 mkdir build
22 cd build
23 cmake .. -DCMAKE_INSTALL_PREFIX=/usr/local
24 make -j"$(nproc)" install
25 ls
26 echo ${CUDA_ARCH_LIST}
27 git clone https://github.com/microsoft/DeepSpeed-Kernels.git ${STAGE_DIR}/DeepSpeed-Kernels
28 cd ${STAGE_DIR}/DeepSpeed-Kernels
29 python -m pip install -v .
30 env
31 python -m pip install -v .
32 git clone https://github.com/microsoft/DeepSpeed.git ${STAGE_DIR}/DeepSpeed
33 cd ${STAGE_DIR}/DeepSpeed
34 export DEEPSPEED_VERSION="v0.14.3"
35 git checkout ${DEEPSPEED_VERSION}
36 ls
37 ./install.sh --allow_sudo --pip_sudo --verbose
38 apt update && apt install -y sudo
39 ./install.sh --allow_sudo --pip_sudo --verbose
```
```shell
nvidia-smi