Efficient management of attention key and value memory with PagedAttention
from vllm import LLM, SamplingParams prompts = [ "Hello, my name is", "The president of the United States is", "The capital of France is", "The future of AI is", ] sampling_params = SamplingParams(temperature=0.8, top_p=0.95) llm = LLM(model="TheBloke/Mistral-7B-OpenOrca-AWQ", quantization="awq", dtype="half") outputs = llm.generate(prompts, sampling_params) # Print the outputs. for output in outputs: prompt = output.prompt generated_text = output.outputs[0].text print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
Log probs
llm = LLM( model=model_name, max_logprobs=tokenizer.vocab_size, ) outputs = llm.generate( texts, SamplingParams(temperature=0.0, logprobs=tokenizer.vocab_size), )
