Instructions to use amd/DeepSeek-V4-Pro-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/DeepSeek-V4-Pro-NVFP4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="amd/DeepSeek-V4-Pro-NVFP4")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("amd/DeepSeek-V4-Pro-NVFP4")
model = AutoModelForCausalLM.from_pretrained("amd/DeepSeek-V4-Pro-NVFP4", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use amd/DeepSeek-V4-Pro-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amd/DeepSeek-V4-Pro-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/DeepSeek-V4-Pro-NVFP4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/amd/DeepSeek-V4-Pro-NVFP4

SGLang

How to use amd/DeepSeek-V4-Pro-NVFP4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "amd/DeepSeek-V4-Pro-NVFP4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/DeepSeek-V4-Pro-NVFP4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "amd/DeepSeek-V4-Pro-NVFP4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/DeepSeek-V4-Pro-NVFP4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use amd/DeepSeek-V4-Pro-NVFP4 with Docker Model Runner:
```
docker model run hf.co/amd/DeepSeek-V4-Pro-NVFP4
```

huidongji commited on Sep 20

Commit

8808a71

verified ·

1 Parent(s): 6f491a9

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -50,7 +50,7 @@ The end-to-end recipe lives in the Quark examples:
 `run_pipeline.sh`. The quantization scope is controlled by `EXCLUDE_LAYERS`.
 ```bash
-export EXCLUDE_LAYERS="*attn* *ffn.gate mtp* *shared_experts*" \
 export SRC=deepseek-ai/DeepSeek-V4-Pro
 export OUT=amd/DeepSeek-V4-Pro-NVFP4
@@ -104,7 +104,7 @@ The model was evaluated on GSM8K benchmarks.
 ### Reproduction
-The GSM8K result was obtained using the `lm-evaluation-harness` framework, based on the Docker image `rocm/vllm-dev:nightly_main_20260714`.
 Install the lm-eval `(Version: 0.4.12)` in container first.
 ```

 `run_pipeline.sh`. The quantization scope is controlled by `EXCLUDE_LAYERS`.
 ```bash
+export EXCLUDE_LAYERS="*ffn.gate *ffn_norm embed head norm mtp*" \
 export SRC=deepseek-ai/DeepSeek-V4-Pro
 export OUT=amd/DeepSeek-V4-Pro-NVFP4
 ### Reproduction
+The GSM8K result was obtained using the `lm-evaluation-harness` framework, based on the Docker image `vllm/vllm-openai-rocm:v0.29.0`.
 Install the lm-eval `(Version: 0.4.12)` in container first.
 ```