Instructions to use Dream-org/Dream-v0-Instruct-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dream-org/Dream-v0-Instruct-7B with Transformers:

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

pipe = pipeline("text-generation", model="Dream-org/Dream-v0-Instruct-7B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Dream-org/Dream-v0-Instruct-7B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dream-org/Dream-v0-Instruct-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dream-org/Dream-v0-Instruct-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dream-org/Dream-v0-Instruct-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dream-org/Dream-v0-Instruct-7B

SGLang

How to use Dream-org/Dream-v0-Instruct-7B 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 "Dream-org/Dream-v0-Instruct-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dream-org/Dream-v0-Instruct-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Dream-org/Dream-v0-Instruct-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dream-org/Dream-v0-Instruct-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Dream-org/Dream-v0-Instruct-7B with Docker Model Runner:
```
docker model run hf.co/Dream-org/Dream-v0-Instruct-7B
```

diffuse-cpp: C++ inference engine for Dream on CPU (GGUF format, Q4_K_M quantization)

by Carmenest - opened Mar 23

Discussion

Carmenest

Mar 23

Hi Dream team! We have built CPU inference support for Dream-v0-Instruct-7B using diffuse-cpp, a C++ inference engine for diffusion language models built on GGML.

Pre-quantized GGUF models

Available at diffuse-cpp/Dream-v0-Instruct-7B-GGUF:

File	Type	Size
dream-7b-f16.gguf	F16	15.2 GB
dream-7b-q8_0.gguf	Q8_0	8.6 GB
dream-7b-q4km.gguf	Q4_K_M	5.3 GB

Performance (Q4_K_M, entropy_exit + inter-step cache, 12 threads)

Prompt	tok/s	Steps	vs llama.cpp
Capital of France?	21.6	2	2.5x
15 x 23?	21.6	2	2.5x
Translate to French	14.3	6	1.7x
Python is_prime()	8.2	7	1.0x
Average	11.6		1.4x

Dream excels at math and code prompts — correctly solves 15x23=345 in just 2 denoising steps at 21.6 tok/s.

Key features

entropy_exit: adaptive scheduler that exits early when the model is confident (2-7 steps for easy prompts vs 16 for hard ones)
Inter-step KV cache: reuses K,V tensors between denoising steps (1.6x average speedup)
Full GQA support: 28 query / 4 KV heads handled natively
QKV biases: preserved at F32 in all quantizations

Comparison with LLaDA-8B

We also support LLaDA-8B. The two models are complementary:

Dream excels at math and code (21.6 tok/s)
LLaDA excels at translation (27.7 tok/s)

Dream-org
/

Dream-v0-Instruct-7B

diffuse-cpp: C++ inference engine for Dream on CPU (GGUF format, Q4_K_M quantization)

Pre-quantized GGUF models

Performance (Q4_K_M, entropy_exit + inter-step cache, 12 threads)

Key features

Comparison with LLaDA-8B

Links