microsoft/Phi-4-multimodal-instruct

Overview

Phi-4-multimodal-instruct processes text, image, and audio inputs and generates text. --trust-remote-code is retained because the model's multimodal LoRA components require it.

Prerequisites

• Hardware: Intel Xeon 6/Xeon 5 CPUs
• vLLM >= 0.8.0

Docker (Intel Xeon 6 CPUs)

docker pull vllm/vllm-openai-cpu:latest-x86_64

Intel Xeon 6

vllm serve microsoft/Phi-4-multimodal-instruct \
  --trust-remote-code  ```

TP/DP values and host-specific CPU placement remain deployment choices and
are not hard-coded into the portable recipe.

## Runtime and Platform Tuning

The following settings are intentionally not prescribed as portable CPU model
defaults because they depend on the workload, hardware, or runtime environment:

- `--max-num-batched-tokens`: scheduler/throughput tuning.
- `--max-num-seqs`: concurrency and scheduler-capacity tuning.
- `--gpu-memory-utilization`: platform memory-budget tuning.
- `--no-enable-prefix-caching`: workload/benchmark cache-policy tuning.
- `VLLM_ENGINE_ITERATION_TIMEOUT_S`: operational runtime timeout.

These settings may still appear in validated hardware-specific overrides. Tune
them at deployment time based on platform resources, workload shape, and
latency/throughput goals.

## References

- [Model card](https://huggingface.co/microsoft/Phi-4-multimodal-instruct)
- [vLLM Phi-4 usage guide](https://docs.vllm.ai/projects/recipes/en/stable/Microsoft/Phi-4.html)
- [vLLM CPU installation](https://docs.vllm.ai/en/latest/getting_started/installation/cpu/)