Instructions to use LLM360/K2-Think with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLM360/K2-Think with Transformers:

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

pipe = pipeline("text-generation", model="LLM360/K2-Think")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LLM360/K2-Think")
model = AutoModelForCausalLM.from_pretrained("LLM360/K2-Think")
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 LLM360/K2-Think with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LLM360/K2-Think"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LLM360/K2-Think",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LLM360/K2-Think

SGLang

How to use LLM360/K2-Think 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 "LLM360/K2-Think" \
    --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": "LLM360/K2-Think",
		"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 "LLM360/K2-Think" \
        --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": "LLM360/K2-Think",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LLM360/K2-Think with Docker Model Runner:
```
docker model run hf.co/LLM360/K2-Think
```

ReasoningParser

by victors2709 - opened Sep 10, 2025

Discussion

victors2709

Sep 10, 2025

•

edited Sep 10, 2025

Hello.
I tried to start with

 vllm/vllm-openai:v0.10.1.1 \
 --model LLM360/K2-Think \
 --tensor-parallel-size 2\
 --disable-log-requests \
 --reasoning-parser qwen3 \
 --enable-auto-tool-choice --tool-call-parser hermes \
 --enable-prompt-tokens-details \
 --port 8002

(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700] EngineCore failed to start.
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700] Traceback (most recent call last):
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 691, in run_engine_core
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700]     engine_core = EngineCoreProc(*args, **kwargs)
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700]                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 492, in __init__
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700]     super().__init__(vllm_config, executor_class, log_stats,
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 96, in __init__
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700]     self.structured_output_manager = StructuredOutputManager(vllm_config)
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700]                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700]   File "/usr/local/lib/python3.12/dist-packages/vllm/v1/structured_output/__init__.py", line 72, in __init__
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700]     self.reasoner = reasoner_cls(tokenizer=self.tokenizer)
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700]                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700]   File "/usr/local/lib/python3.12/dist-packages/vllm/reasoning/qwen3_reasoning_parser.py", line 43, in __init__
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700]     raise RuntimeError(
(EngineCore_0 pid=270) ERROR 09-10 07:52:08 [core.py:700] RuntimeError: Qwen3 reasoning parser could not locate think start/end tokens in the tokenizer!

richardmfan

LLM360 org Sep 10, 2025

The base model for K2-Think is Qwen2.5-32B. <think> and </think> do not appear as special tokens as they do in Qwen3.

aaryamonvikram changed discussion status to closed Sep 12, 2025

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