3.5.1

What's new?

• Add support for Qwen3 in #1300.

  Example usage:

  import { pipeline, TextStreamer } from "@huggingface/transformers";
  
  // Create a text generation pipeline
  const generator = await pipeline(
    "text-generation",
    "onnx-community/Qwen3-0.6B-ONNX",
    { dtype: "q4f16", device: "webgpu" },
  );
  
  // Define the list of messages
  const messages = [
    { role: "user", content: "If 5 brog 5 is 1, and 4 brog 2 is 2, what is 3 brog 1?" },
  ];
  
  // Generate a response
  const output = await generator(messages, {
      max_new_tokens: 1024,
      do_sample: true,
      top_k: 20,
      temperature: 0.7,
      streamer: new TextStreamer(generator.tokenizer, { skip_prompt: true, skip_special_tokens: true}),
  });
  console.log(output[0].generated_text.at(-1).content);

  Try out the online demo:

  qwen3-webgpu.mp4

• Add support for D-FINE in #1303

  Example usage:

  import { pipeline } from "@huggingface/transformers";
  
  const detector = await pipeline("object-detection", "onnx-community/dfine_s_coco-ONNX");
  
  const image = "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/cats.jpg";
  const output = await detector(image, { threshold: 0.5 });
  console.log(output);

  See list of supported models: https://huggingface.co/models?library=transformers.js&other=d_fine&sort=trending

• Introduce global inference chain (+ other WebGPU fixes) in #1293

• fix: RawImage.fromURL error when input file url by @himself65 in #1288

• [bugfix] tokenizers respect padding: true with non-null max_length by @dwisdom0 in #1284

New Contributors

• @himself65 made their first contribution in #1288
• @dwisdom0 made their first contribution in #1284

Full Changelog: 3.5.0...3.5.1