Instructions to use IFM/K2-Horizon-375B-A23B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IFM/K2-Horizon-375B-A23B-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="IFM/K2-Horizon-375B-A23B-FP8", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("IFM/K2-Horizon-375B-A23B-FP8", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IFM/K2-Horizon-375B-A23B-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IFM/K2-Horizon-375B-A23B-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IFM/K2-Horizon-375B-A23B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IFM/K2-Horizon-375B-A23B-FP8

SGLang

How to use IFM/K2-Horizon-375B-A23B-FP8 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 "IFM/K2-Horizon-375B-A23B-FP8" \
    --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": "IFM/K2-Horizon-375B-A23B-FP8",
		"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 "IFM/K2-Horizon-375B-A23B-FP8" \
        --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": "IFM/K2-Horizon-375B-A23B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IFM/K2-Horizon-375B-A23B-FP8 with Docker Model Runner:
```
docker model run hf.co/IFM/K2-Horizon-375B-A23B-FP8
```

mingshan commited on 7 days ago

Commit

008d268

verified ·

1 Parent(s): 39f8059

Update README.md

Browse files

Add expert parallelism to vLLM and SGLang serving cookbook

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -66,12 +66,13 @@ vllm serve IFM/K2-Horizon-375B-A23B \
   --revision main \
   --model-impl transformers \
   --tensor-parallel-size 8 \
   --trust-remote-code \
   --dtype bfloat16 \
   --max-model-len 131072 \
   --reasoning-parser k2_horizon \
-  --enable-auto-tool-choice \
-  --tool-call-parser k2_horizon
 ```
 SGLang recipe validated on 8× H200 in the [SGLang K2 Horizon cookbook](https://docs.sglang.io/cookbook/autoregressive/IFM/K2-Horizon):
@@ -81,6 +82,7 @@ python3 -m sglang.launch_server \
   --model-path IFM/K2-Horizon-375B-A23B \
   --revision main \
   --tp 8 \
   --dtype bfloat16 \
   --attention-backend fa3 \
   --model-loader-extra-config '{"enable_multithread_load":false}' \

   --revision main \
   --model-impl transformers \
   --tensor-parallel-size 8 \
+  --enable-expert-parallel \
   --trust-remote-code \
   --dtype bfloat16 \
   --max-model-len 131072 \
   --reasoning-parser k2_horizon \
+  --tool-call-parser k2_horizon \
+  --enable-auto-tool-choice
 ```
 SGLang recipe validated on 8× H200 in the [SGLang K2 Horizon cookbook](https://docs.sglang.io/cookbook/autoregressive/IFM/K2-Horizon):
   --model-path IFM/K2-Horizon-375B-A23B \
   --revision main \
   --tp 8 \
+  --ep 8 \
   --dtype bfloat16 \
   --attention-backend fa3 \
   --model-loader-extra-config '{"enable_multithread_load":false}' \