Instructions to use openai/gpt-oss-120b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openai/gpt-oss-120b with Transformers:

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

pipe = pipeline("text-generation", model="openai/gpt-oss-120b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openai/gpt-oss-120b")
model = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-120b", device_map="auto")
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
HuggingChat
Notebooks
Google Colab
Kaggle
AMD Developer Cloud
Local Apps Settings

vLLM

How to use openai/gpt-oss-120b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openai/gpt-oss-120b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openai/gpt-oss-120b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openai/gpt-oss-120b

SGLang

How to use openai/gpt-oss-120b 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 "openai/gpt-oss-120b" \
    --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": "openai/gpt-oss-120b",
		"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 "openai/gpt-oss-120b" \
        --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": "openai/gpt-oss-120b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openai/gpt-oss-120b with Docker Model Runner:
```
docker model run hf.co/openai/gpt-oss-120b
```

Failed in vllm inference

#139

by Mqleet - opened Sep 8, 2025

Discussion

Mqleet

Sep 8, 2025

Hello, thanks for your great work! I met the failed info below:

[1;36m(EngineCore_0 pid=3481)[0;0m ERROR 09-08 23:05:16 [backend_xgrammar.py:163] Failed to advance FSM for request chatcmpl-c9d0e134de19488db8c73c97a2f23bae for tokens 4050. Please file an issue.
[1;36m(EngineCore_0 pid=3481)[0;0m ERROR 09-08 23:05:16 [backend_xgrammar.py:163] Failed to advance FSM for request chatcmpl-105ce5912c5e48b8b417cca36e8bd3b0 for tokens 2601. Please file an issue.
[1;36m(EngineCore_0 pid=3481)[0;0m ERROR 09-08 23:05:16 [backend_xgrammar.py:163] Failed to advance FSM for request chatcmpl-105ce5912c5e48b8b417cca36e8bd3b0 for tokens 200012. Please file an issue.
[1;36m(APIServer pid=3042)[0;0m INFO:     127.0.0.1:36242 - "POST /v1/chat/completions HTTP/1.1" 200 OK
[1;36m(EngineCore_0 pid=3481)[0;0m ERROR 09-08 23:05:16 [backend_xgrammar.py:163] Failed to advance FSM for request chatcmpl-d7489a05165e43d8aa1aff25866de331 for tokens 256. Please file an issue.
[1;36m(APIServer pid=3042)[0;0m INFO:     127.0.0.1:36208 - "POST /v1/chat/completions HTTP/1.1" 200 OK
[1;36m(EngineCore_0 pid=3481)[0;0m ERROR 09-08 23:05:17 [backend_xgrammar.py:163] Failed to advance FSM for request chatcmpl-5ea7e4163e574c34990d1b390d6971d7 for tokens 1202. Please file an issue.
[1;36m(APIServer pid=3042)[0;0m INFO:     127.0.0.1:36152 - "POST /v1/chat/completions HTTP/1.1" 200 OK
[1;36m(EngineCore_0 pid=3481)[0;0m ERROR 09-08 23:05:17 [backend_xgrammar.py:163] Failed to advance FSM for request chatcmpl-6016d82b12154fe385620e843185458b for tokens 3369. Please file an issue.
[1;36m(EngineCore_0 pid=3481)[0;0m ERROR 09-08 23:05:17 [backend_xgrammar.py:163] Failed to advance FSM for request chatcmpl-6016d82b12154fe385620e843185458b for tokens 175728. Please file an issue.
[1;36m(EngineCore_0 pid=3481)[0;0m ERROR 09-08 23:05:17 [backend_xgrammar.py:163] Failed to advance FSM for request chatcmpl-6016d82b12154fe385620e843185458b for tokens 18583. Please file an issue.
[1;36m(APIServer pid=3042)[0;0m INFO:     127.0.0.1:36220 - "POST /v1/chat/completions HTTP/1.1" 200 OK
[1;36m(EngineCore_0 pid=3481)[0;0m ERROR 09-08 23:05:17 [backend_xgrammar.py:163] Failed to advance FSM for request chatcmpl-5abbcb233a90485f96016ee2fa5c43c7 for tokens 3369. Please file an issue.
[1;36m(EngineCore_0 pid=3481)[0;0m ERROR 09-08 23:05:17 [backend_xgrammar.py:163] Failed to advance FSM for request chatcmpl-c9d0e134de19488db8c73c97a2f23bae for tokens 279. Please file an issue.
[1;36m(EngineCore_0 pid=3481)[0;0m ERROR 09-08 23:05:18 [backend_xgrammar.py:163] Failed to advance FSM for request chatcmpl-5abbcb233a90485f96016ee2fa5c43c7 for tokens 388. Please file an issue.

and the vllm commands is:

vllm serve openai/gpt-oss-120b \
    --async-scheduling \
    --port 11451 \
    --host 0.0.0.0 \
    --tensor-parallel-size $NUM_GPUS \
    --max-model-len 131072 \
    --gpu-memory-utilization 0.8 \

How can I solve this problem?

dhanrajkatkar

Nov 20, 2025

Try removing --async-scheduling, it is unstable as of now reference

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