How to parallelize this code for model.generate?

[ryanshrott]

As the title says, how can I parallelize this?

def generate_output(row):
      inputs = tokenizer(prompt, return_tensors="pt")["input_ids"]
      outputs = model.generate(inputs, max_new_tokens=185, temperature=0.0, eos_token_id=tokenizer.encode("}")[0])
      result = tokenizer.decode(outputs[0])
      completion = extract_completion(result)

for index, row in df.iterrows():
  generate_output(row)