Instructions to use FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2 with Transformers:

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

pipe = pipeline("text-generation", model="FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2")
model = AutoModelForCausalLM.from_pretrained("FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2

SGLang

How to use FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2 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 "FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2" \
    --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": "FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2",
		"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 "FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2" \
        --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": "FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2 with Docker Model Runner:
```
docker model run hf.co/FastFlowLM/Deepseek-R1-Distill-Llama-8B-NPU2
```

Deepseek-R1-Distill-Llama-8B-NPU2

Commit History

feat: remove xclbins

a375d44

ngdxzy commited on May 25

Revert "feat: remove all xclbins from model"

abaad98

ngdxzy commited on May 25

feat: update chat template

60cd990

ngdxzy commited on May 25

feat: remove all xclbins from model

7103bdc

ngdxzy commited on May 25

feat: new mm

9305875

ngdxzy commited on Jan 7

feat: fix tokenizer

4e50d20

ngdxzy commited on Nov 23, 2025

feat: merge lm head

c49fa14

ngdxzy commited on Nov 22, 2025

Update README.md

deca786
verified

FastFlowLM commited on Aug 11, 2025

Update README.md

91dc357
verified

FastFlowLM commited on Aug 11, 2025

Create README.md

8deccd0
verified

FastFlowLM commited on Jul 31, 2025

Update config.json

1902964
verified

FastFlowLM commited on Jul 26, 2025

update_mm

59fffc3

ngdxzy commited on Jul 25, 2025

update_glu

d77ceb2

ngdxzy commited on Jul 16, 2025

Upload tokenizer_config.json

16ac420
verified

FastFlowLM commited on Jul 9, 2025

updateMM

fb69208

ngdxzy commited on Jun 13, 2025

support_prefill

94e495f

ngdxzy commited on Jun 13, 2025

add_bin

cea47d5

ngdxzy commited on May 23, 2025

addatt

5770a06

ngdxzy commited on May 15, 2025

init

4ff9fbd

ngdxzy commited on May 15, 2025

Commit History

feat: remove xclbins a375d44

Revert "feat: remove all xclbins from model" abaad98

feat: update chat template 60cd990

feat: remove all xclbins from model 7103bdc

feat: new mm 9305875

feat: fix tokenizer 4e50d20

feat: merge lm head c49fa14

Update README.md deca786 verified

Update README.md 91dc357 verified

Create README.md 8deccd0 verified

Update config.json 1902964 verified

update_mm 59fffc3

update_glu d77ceb2

Upload tokenizer_config.json 16ac420 verified

updateMM fb69208

support_prefill 94e495f

add_bin cea47d5

addatt 5770a06

init 4ff9fbd

feat: remove xclbins

a375d44

Revert "feat: remove all xclbins from model"

abaad98

feat: update chat template

60cd990

feat: remove all xclbins from model

7103bdc

feat: new mm

9305875

feat: fix tokenizer

4e50d20

feat: merge lm head

c49fa14

Update README.md

deca786
verified

Update README.md

91dc357
verified

Create README.md

8deccd0
verified

Update config.json

1902964
verified

update_mm

59fffc3

update_glu

d77ceb2

Upload tokenizer_config.json

16ac420
verified

updateMM

fb69208

support_prefill

94e495f

add_bin

cea47d5

addatt

5770a06

init

4ff9fbd