大模型系列——投机解码:Prompt Lookup Decoding代码解读

官方代码见:GitHub - apoorvumang/prompt-lookup-decoding

UPDATE 2 : This method is now available in vLLM as well by setting speculative_model="[ngram]" 🥳

UPDATE : This has been added to the transformers library. Please see this for a code example, or simply add prompt_lookup_num_tokens=10 to your model.generate(...) call.

TLDR : We modify speculative decoding where we replace the draft model with simple string matching in the prompt to generate candidate token sequences. This results in significant speedups (2x-4x) in input-grounded tasks, with no effect on output quality. This method can be used with any decoder model without model changes or external datastore, and with both greedy and sampling techniques.

Intuition : In several LLM use cases where you're doing input grounded generation (summarization, document QA, multi-turn chat, code editing), there is high n-gram overlap between LLM input (prompt) and LLM output. This could be entity names, phrases, or code chunks that the LLM directly copies from the input while generating the output. Prompt lookup exploits this pattern to speed up autoregressive decoding in LLMs.

python 复制代码
def find_candidate_pred_tokens(input_ids, max_ngram_size=3, num_pred_tokens=10):
    input_length = input_ids.size(1)

    for ngram_size in range(max_ngram_size, 0, -1):
        # Extract the last n tokens as our search ngram
        ngram = input_ids[0, -ngram_size:].tolist()

        # Create sliding windows of size ngram_size
        windows = input_ids.unfold(dimension=1, size=ngram_size, step=1)

        # Convert ngram to a tensor for comparison
        ngram_tensor = torch.tensor(ngram, device=input_ids.device).unsqueeze(0)

        # Find where the windows match the ngram
        matches = (windows == ngram_tensor).all(dim=2)

        # Get the indices of matches
        match_indices = matches.nonzero(as_tuple=True)[1]

        # Iterate through match indices to find a valid continuation
        for idx in match_indices:
            start_idx = idx + ngram_size
            end_idx = start_idx + num_pred_tokens
            # Ensure we don't go beyond the length of input_ids and avoid self-match
            if end_idx <= input_length and start_idx < input_length - ngram_size:
                return input_ids[0, start_idx:end_idx]

    # If no match is found, return an empty tensor
    return torch.tensor([], dtype=torch.long, device=input_ids.device)

ODOs/Thoughts/Future work

  • There's probably better ways to do stringmatching than the current one, and there are several obvious things to improve eg. what to do when there are multiple matches? Whats the ideal length of continuation?
  • We haven't yet tried sampling, although there's no reason it shouldn't work.
    • Here, one additional thing to test would be whether prompt lookup while sampling can affect hallucination rates, since this artifically increases probability of sampling exact sequences from input (this was suggest by my colleague Shwetha S)
  • Testing actual FLOPs impact and tradeoffs is needed
  • Also need to figure out best hyperparams - 3 and 10 were chosen on very little testing
  • It would be an interesting challenge to design the "best lookup function" for decoding, could even be a competition?

这个方法可能还是有问题的,正如坐着所说,可能存在幻觉,不一定ngram匹配上的就能加速

相关推荐
姚瑞南16 小时前
【Prompt实战】广告营销客服专家
人工智能·chatgpt·prompt·aigc
云梦之上20 小时前
视觉风格提示词:Visual Style Prompting with Swapping Self-Attention(风格迁移)
pytorch·python·计算机视觉·ai作画·prompt
Golinie1 天前
使用Ollama+Langchaingo+Gin通过定义prompt模版实现翻译功能
llm·prompt·gin·langchaingo
L_cl1 天前
【NLP 49、提示工程 prompt engineering】
prompt
小猪皮蛋粥1 天前
VScode配置默认终端为Anaconda Prompt
ide·vscode·prompt
SanMu三木2 天前
LangChain 基础系列之 Prompt 工程详解:从设计原理到实战模板
langchain·prompt
三月七(爱看动漫的程序员)2 天前
TAPO: Task-Referenced Adaptation for Prompt Optimization
人工智能·gpt·机器学习·语言模型·自然语言处理·prompt·集成学习
放羊郎2 天前
本地文生图使用插件(Stable Diffusion)
stable diffusion·prompt·插件
早茶和猫3 天前
【YOLOE: Real-Time Seeing Anything】predict_visual_prompt.py视觉推理代码分析(检测版本)
yolo·目标检测·prompt·yoloe·视觉提示·开放检测
He.Tech4 天前
提示词工程(Prompt Engineering):释放AI潜能的“语言编程”
人工智能·prompt