Instructions to use Kwaipilot/KAT-Dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kwaipilot/KAT-Dev with Transformers:

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

pipe = pipeline("text-generation", model="Kwaipilot/KAT-Dev")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kwaipilot/KAT-Dev")
model = AutoModelForCausalLM.from_pretrained("Kwaipilot/KAT-Dev")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Kwaipilot/KAT-Dev with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Kwaipilot/KAT-Dev

SGLang

How to use Kwaipilot/KAT-Dev 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 "Kwaipilot/KAT-Dev" \
    --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": "Kwaipilot/KAT-Dev",
		"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 "Kwaipilot/KAT-Dev" \
        --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": "Kwaipilot/KAT-Dev",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kwaipilot/KAT-Dev with Docker Model Runner:
```
docker model run hf.co/Kwaipilot/KAT-Dev
```

evaluation methodology for humaneval

#15

by viplismism - opened Nov 21, 2025

Discussion

viplismism

Nov 21, 2025

hey hi @shunxing1234 and @arieldeng

Congrats on the impressive KAT-Coder results!
I'm trying to replicate your HumanEval evaluation to benchmark my own models. Could you clarify:

What temperature did you use for HumanEval (96.3% in Table 1)
Is this pass@1 or pass@k? If pass@k, what's k and n?
Did you use the Python HumanEval or MultiPL-E (Rust/other language)?

akierum

Mar 16

I would be interested if you can replicate them. this model is smart, but not working with roocode, cline etc.
Devs do not update or fix it.

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