Instructions to use RadixArk/Kimi-K3-DSpark with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RadixArk/Kimi-K3-DSpark with Transformers:

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

pipe = pipeline("text-generation", model="RadixArk/Kimi-K3-DSpark", trust_remote_code=True)

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

tokenizer = AutoTokenizer.from_pretrained("RadixArk/Kimi-K3-DSpark", trust_remote_code=True)
model = AutoModel.from_pretrained("RadixArk/Kimi-K3-DSpark", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RadixArk/Kimi-K3-DSpark with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RadixArk/Kimi-K3-DSpark"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RadixArk/Kimi-K3-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RadixArk/Kimi-K3-DSpark

SGLang

How to use RadixArk/Kimi-K3-DSpark 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 "RadixArk/Kimi-K3-DSpark" \
    --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": "RadixArk/Kimi-K3-DSpark",
		"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 "RadixArk/Kimi-K3-DSpark" \
        --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": "RadixArk/Kimi-K3-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RadixArk/Kimi-K3-DSpark with Docker Model Runner:
```
docker model run hf.co/RadixArk/Kimi-K3-DSpark
```

DSpark accept rate is under 0.5, what should I do next?

by zzyong - opened Sep 11

Discussion

zzyong

Sep 11

I use this dspark draft model, accept rate is only 0.45 ~ 0.5, accept len is 2 ( I use --speculative-dspark-block-size 2).
I had try other dspark draft model on hugging face, it's accept rate is worse then this one.
why? what should I do if I want to raise the accept rate.

cmRDXA

Sep 11

Have you tried the --speculative-dspark-block-size 7?
What is the acc len on this block size?

zzyong

Sep 16

Have you tried the --speculative-dspark-block-size 7?
What is the acc len on this block size?

I try --speculative-dspark-block-size 7, the accept len is 2.5, a little improved, but verify cost higher, so I use block-size 2.

cfbdsir

22 days ago

We've encountered the same problem too. Have you managed to solve it? What was causing the issue, or does it need to be retrained?

zzyong

21 days ago

We've encountered the same problem too. Have you managed to solve it? What was causing the issue, or does it need to be retrained?

We are studying how to retrain.

cfbdsir

21 days ago

•

edited 21 days ago

We've encountered the same problem too. Have you managed to solve it? What was causing the issue, or does it need to be retrained?

We are studying how to retrain.

OK,I am also studying retraining.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment