Deploy DeepSeek on a Cloud GPU

runcrate instances create --name deepseek-8b --gpu RTX4090
runcrate instances status deepseek-8b

runcrate ssh deepseek-8b -- "pip install vllm"

runcrate ssh deepseek-8b -- "nohup python -m vllm.entrypoints.openai.api_server \
  --model deepseek-ai/DeepSeek-R1-Distill-Llama-8B \
  --max-model-len 8192 \
  --port 8000 --host 0.0.0.0 \
  > /root/vllm.log 2>&1 &"

runcrate instances create --name deepseek-70b --gpu A100
runcrate ssh deepseek-70b -- "pip install vllm"

runcrate ssh deepseek-70b -- "nohup python -m vllm.entrypoints.openai.api_server \
  --model deepseek-ai/DeepSeek-R1-Distill-Llama-70B \
  --max-model-len 8192 \
  --port 8000 --host 0.0.0.0 \
  > /root/vllm.log 2>&1 &"

runcrate instances create --name deepseek-v3 --gpu H100 --gpu-count 4
runcrate ssh deepseek-v3 -- "pip install vllm"

runcrate ssh deepseek-v3 -- "nohup python -m vllm.entrypoints.openai.api_server \
  --model deepseek-ai/DeepSeek-V3 \
  --tensor-parallel-size 4 \
  --max-model-len 16384 \
  --trust-remote-code \
  --port 8000 --host 0.0.0.0 \
  > /root/vllm.log 2>&1 &"

runcrate instances info deepseek-8b

curl http://<INSTANCE_IP>:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
    "messages": [{"role": "user", "content": "Explain mixture-of-experts in two sentences."}],
    "max_tokens": 256
  }'

runcrate ssh deepseek-8b -- nvidia-smi
runcrate ssh deepseek-8b -- "tail -50 /root/vllm.log"

runcrate instances delete deepseek-8b
runcrate instances delete deepseek-70b
runcrate instances delete deepseek-v3