Set HF_TOKEN in the host environment. Container image: vllm/vllm-openai:v0.31.0
docker run --rm -it \
--gpus all \
--ipc host \
--network host \
--shm-size=16g \
--ulimit memlock=-1 \
--ulimit stack=67108864 \
-e HF_TOKEN=$HF_TOKEN \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--entrypoint /bin/bash \
vllm/vllm-openai:v0.31.0
vllm serve deepseek-ai/DeepSeek-V4-Flash-0731 \
--served-model-name deepseek-v4-flash-0731 \
--host 0.0.0.0 --port 8000 \
--trust-remote-code \
--tensor-parallel-size 1 \
--kv-cache-dtype fp8_ds_mla \
--block-size 256 \
--max-model-len 1048576 \
--max-num-seqs 64 \
--max-num-batched-tokens 32768 \
--max-cudagraph-capture-size 512 \
--gpu-memory-utilization 0.88 \
--enable-prefix-caching \
--enable-prompt-tokens-details \
--async-scheduling \
--enable-chunked-prefill \
--speculative-config '{"method":"dspark","num_speculative_tokens":7,"draft_sample_method":"probabilistic"}' \
--tokenizer-mode deepseek_v4 \
--tool-call-parser deepseek_v4 --enable-auto-tool-choice \
--reasoning-parser deepseek_v4 \
--generation-config vllm \
--compilation-config '{"custom_ops":["all"]}'