Instructions to use Kwaipilot/KAT-Dev-72B-Exp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kwaipilot/KAT-Dev-72B-Exp with Transformers:

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

pipe = pipeline("text-generation", model="Kwaipilot/KAT-Dev-72B-Exp")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kwaipilot/KAT-Dev-72B-Exp")
model = AutoModelForCausalLM.from_pretrained("Kwaipilot/KAT-Dev-72B-Exp")
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-72B-Exp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kwaipilot/KAT-Dev-72B-Exp"
# 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-72B-Exp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kwaipilot/KAT-Dev-72B-Exp

SGLang

How to use Kwaipilot/KAT-Dev-72B-Exp 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-72B-Exp" \
    --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-72B-Exp",
		"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-72B-Exp" \
        --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-72B-Exp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kwaipilot/KAT-Dev-72B-Exp with Docker Model Runner:
```
docker model run hf.co/Kwaipilot/KAT-Dev-72B-Exp
```

Context Length Exceeded Issue - Difference between Official SWE-agent and Mini SWE-agent

#12

by skywalker317 - opened Oct 16, 2025

Discussion

skywalker317

Oct 16, 2025

•

edited Oct 16, 2025

Hi team,

I’m trying to reproduce the evaluation results of your model, but encountering some issues regarding context length management.

My Setup:
Using mini swe-agent framework (only bash tool available)
Set context length to 128k
Still frequently hitting “exceed context limit” errors

Official Setup (from your repo):
Using full SWE-agent (bash, str_replace_editor, submit tools)
Only used 85k context length
Achieved good results without context issues
Questions:

Why does the official setup with 85k context work better than my 128k setup?
Is the difference mainly due to the additional tools (str_replace_editor, submit)?
Do these tools help reduce context consumption?
Are there any specific context management strategies used in the official evaluation?
Could you share more details about the context window management in your evaluation setup?
Any guidance would be greatly appreciated!

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