apt update
apt install -y gpg-agent wget
wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null
echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list
apt update

apt install -y intel-oneapi-base-toolkit
#

. /opt/intel/oneapi/2025.1/oneapi-vars.sh
oneapi-cli

#apt -y install intel-cpp-essentials
#apt -y install cmake pkg-config build-essential

wget https://registrationcenter-download.intel.com/akdlm/IRC_NAS/491d5c2a-67fe-48d0-884f-6aecd88f5d8a/ai-tools-2025.0.0.75_offline.sh
sh ai-tools-2025.0.0.75_offline.sh

wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
echo "deb https://apt.repos.intel.com/openvino ubuntu24 main" | sudo tee /etc/apt/sources.list.d/intel-openvino.list
sudo apt update
apt-cache search openvino
sudo apt install openvino-2025.1.0

wget https://github.com/openvinotoolkit/model_server/releases/download/v2025.1/ovms_ubuntu24_python_on.tar.gz
tar -xzvf ovms_ubuntu24_python_on.tar.gz
export LD_LIBRARY_PATH=${PWD}/ovms/lib
export PATH=$PATH:${PWD}/ovms/bin
curl --create-dirs -k https://storage.openvinotoolkit.org/repositories/open_model_zoo/2022.1/models_bin/2/resnet50-binary-0001/FP32-INT1/resnet50-binary-0001.xml -o models/resnet50/1/model.xml
curl --create-dirs -k https://storage.openvinotoolkit.org/repositories/open_model_zoo/2022.1/models_bin/2/resnet50-binary-0001/FP32-INT1/resnet50-binary-0001.bin -o models/resnet50/1/model.bin
chmod -R 755 models
export PYTHONPATH=${PWD}/ovms/lib/python
sudo apt -y install libpython3.12
pip3 install "Jinja2==3.1.6" "MarkupSafe==3.0.2"
ovms --port 9000 --model_name resnet --model_path models/resnet50

sudo apt update
sudo apt upgrade
sudo add-apt-repository ppa:deadsnakes/ppa
sudo apt install python3.11 -y
sudo apt install python3.11-venv -y
python3.11 -V
python3.11 -m venv llm_env
source llm_env/bin/activate
pip install --pre --upgrade ipex-llm[cpp]
mkdir llama-cpp
cd llama-cpp
# Run Ollama Serve with Intel GPU
export OLLAMA_NUM_GPU=128
export no_proxy=localhost,127.0.0.1
export ZES_ENABLE_SYSMAN=1
source /opt/intel/oneapi/setvars.sh
export SYCL_CACHE_PERSISTENT=1
# localhost access
# ./ollama serve
# for non-localhost access
OLLAMA_HOST=0.0.0.0 ./ollama serve

(base) root@server1:~/llama-cpp# ./ollama list
NAME               ID              SIZE     MODIFIED
qwen3:32b          e1c9f234c6eb    20 GB    28 minutes ago
gemma3:27b         a418f5838eaf    17 GB    37 minutes ago
deepseek-r1:70b    0c1615a8ca32    42 GB    About an hour ago

(base) root@server1:~/llama-cpp# ./ollama list
NAME               ID              SIZE     MODIFIED
qwen3:32b          e1c9f234c6eb    20 GB    28 minutes ago
gemma3:27b         a418f5838eaf    17 GB    37 minutes ago
deepseek-r1:70b    0c1615a8ca32    42 GB    About an hour ago
(base) root@server1:~/llama-cpp# ./ollama pull openchat:7b
pulling manifest
pulling 1cecc26325a1... 100% ▕████████████████████████████████████████████████████████████████████████████████ ▏ 4.1 GB/4.1 GB  102 MB/s      0s
pulling 43070e2d4e53... 100% ▕████████████████████████████████████████████████████████████████████████████████▏  11 KB
pulling d68706c17530... 100% ▕████████████████████████████████████████████████████████████████████████████████▏   98 B
pulling 415f0f6b43dd... 100% ▕████████████████████████████████████████████████████████████████████████████████▏   65 B
pulling 278996753456... 100% ▕████████████████████████████████████████████████████████████████████████████████▏  483 B
verifying sha256 digest
writing manifest
success

source llm_env/bin/activate
#pip install open-webui==0.2.5
pip install open-webui # 0.6.10
open-webui serve

apt install -y libcurl-ocaml-dev
git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp
cmake -B build
cmake --build build --config Release
cd build
make install
ldconfig

llama-cli -m model.gguf
llama-server -m model.gguf --port 8080
llama-bench -m model.gguf
llama-run