async function generate()

in zyphra-zr1-webgpu/src/worker.js [51:128]
64 lines of code
3 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,
  });

  // 151648: <think>
  // 151649: </think>
  const [START_THINKING_TOKEN_ID, END_THINKING_TOKEN_ID] = tokenizer.encode(
    "<think></think>",
    { add_special_tokens: false },
  );

  let state = "thinking"; // 'thinking' or 'answering'
  let startTime;
  let numTokens = 0;
  let tps;
  const token_callback_function = (tokens) => {
    startTime ??= performance.now();

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

  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 back when fixed
    // past_key_values: past_key_values_cache,

    // Sampling
    do_sample: false,
    // repetition_penalty: 1.1,
    // top_k: 3,
    // temperature: 0.2,

    max_new_tokens: 2048,
    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,
  });
}