Instructions to use Kwaipilot/KAT-Coder-V2.5-Dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kwaipilot/KAT-Coder-V2.5-Dev with Transformers:

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

pipe = pipeline("text-generation", model="Kwaipilot/KAT-Coder-V2.5-Dev")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Kwaipilot/KAT-Coder-V2.5-Dev")
model = AutoModelForMultimodalLM.from_pretrained("Kwaipilot/KAT-Coder-V2.5-Dev", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kwaipilot/KAT-Coder-V2.5-Dev with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kwaipilot/KAT-Coder-V2.5-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-Coder-V2.5-Dev",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kwaipilot/KAT-Coder-V2.5-Dev

SGLang

How to use Kwaipilot/KAT-Coder-V2.5-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-Coder-V2.5-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-Coder-V2.5-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-Coder-V2.5-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-Coder-V2.5-Dev",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kwaipilot/KAT-Coder-V2.5-Dev with Docker Model Runner:
```
docker model run hf.co/Kwaipilot/KAT-Coder-V2.5-Dev
```

KAT-Coder-V2.5-Dev — Solid pick for Claude Code + Superpowers

#28

by darkmatter2222 - opened 10 days ago

Discussion

darkmatter2222

10 days ago

Been running the KAT-Coder-V2.5-Dev model and it's been by far the best for me when paired with Claude Code and the Superpowers plugin.

Setup:
exec /opt/vllm025/bin/vllm serve
/home/darkmatter2222/models/KAT-Coder-V2.5-Dev-NVFP4
--served-model-name kat-coder-v2.5
--host 0.0.0.0
--port 8006
--trust-remote-code
--dtype auto
--language-model-only
--chat-template /var/log/vllm/kat-chat-template-runtime.jinja
--performance-mode throughput
--no-enable-log-requests
--gpu-memory-utilization 0.85
--max-model-len 262146
--max-num-seqs 12
--max-num-batched-tokens 16384
--enable-prefix-caching
--enable-chunked-prefill
--enable-auto-tool-choice
--tool-call-parser qwen3_coder
--reasoning-parser qwen3
--kv-cache-memory-bytes 17179869184
--kv-cache-dtype fp8
--no-async-scheduling
--gdn-prefill-backend triton
--compilation-config '{"cudagraph_mode":"PIECEWISE","cudagraph_capture_sizes":[1,2,4,8,12]}'

Results: ~50 TPS single concurrency, no MTP.

Would love to see MTP support in future — that's the only thing I'm missing right now. Otherwise, very impressed with this one.

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