async function generate()

in llama-3.2-webgpu/src/worker.js [32:94]

• 52 lines of code
• 2 McCabe index (conditional complexity)

async function generate(messages) {
  // Retrieve the text-generation pipeline.
  const [tokenizer, model] = await TextGenerationPipeline.getInstance();

  const inputs = tokenizer.apply_chat_template(messages, {
    add_generation_prompt: true,
    return_dict: true,
  });

  let startTime;
  let numTokens = 0;
  let tps;
  const token_callback_function = () => {
    startTime ??= performance.now();

    if (numTokens++ > 0) {
      tps = (numTokens / (performance.now() - startTime)) * 1000;
    }
  };
  const callback_function = (output) => {
    self.postMessage({
      status: "update",
      output,
      tps,
      numTokens,
    });
  };

  const streamer = new TextStreamer(tokenizer, {
    skip_prompt: true,
    skip_special_tokens: true,
    callback_function,
    token_callback_function,
  });

  // Tell the main thread we are starting
  self.postMessage({ status: "start" });

  const { past_key_values, sequences } = await model.generate({
    ...inputs,
    // TODO: Add when model is fixed
    // past_key_values: past_key_values_cache,

    // Sampling
    do_sample: false,

    max_new_tokens: 1024,
    streamer,
    stopping_criteria,
    return_dict_in_generate: true,
  });
  // past_key_values_cache = past_key_values;

  const decoded = tokenizer.batch_decode(sequences, {
    skip_special_tokens: true,
  });

  // Send the output back to the main thread
  self.postMessage({
    status: "complete",
    output: decoded,
  });
}