Instructions to use silx-ai/Quasar-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use silx-ai/Quasar-Preview with Transformers:

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

pipe = pipeline("text-generation", model="silx-ai/Quasar-Preview", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("silx-ai/Quasar-Preview", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use silx-ai/Quasar-Preview with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/silx-ai/Quasar-Preview

SGLang

How to use silx-ai/Quasar-Preview 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 "silx-ai/Quasar-Preview" \
    --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": "silx-ai/Quasar-Preview",
		"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 "silx-ai/Quasar-Preview" \
        --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": "silx-ai/Quasar-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use silx-ai/Quasar-Preview with Docker Model Runner:
```
docker model run hf.co/silx-ai/Quasar-Preview
```

Quasar-Preview / fla /ops /retention /fused_recurrent.py

eyad-silx

Quasar-preview

df13683 verified 3 months ago

Raw

History Blame

898 Bytes

	# Copyright (c) 2023-2025, Songlin Yang, Yu Zhang


	import torch

	from fla.ops.simple_gla.fused_recurrent import fused_recurrent_simple_gla


	def fused_recurrent_retention(
	q: torch.Tensor,
	k: torch.Tensor,
	v: torch.Tensor,
	scale: float \| None = None,
	initial_state: torch.Tensor \| None = None,
	output_final_state: bool = False,
	reverse: bool = False,
	cu_seqlens: torch.LongTensor \| None = None,
	) -> tuple[torch.Tensor, torch.Tensor]:
	g_gamma = (1 - q.new_tensor(2., dtype=torch.float).pow(-5. - q.new_tensor(range(q.shape[2]), dtype=torch.float))).log()
	o, final_state = fused_recurrent_simple_gla(
	q=q,
	k=k,
	v=v,
	g_gamma=g_gamma,
	scale=scale,
	initial_state=initial_state,
	output_final_state=output_final_state,
	reverse=reverse,
	cu_seqlens=cu_seqlens,
	)
	return o, final_state