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
0x21111 小时前
[论文精读]StruQ: Defending Against Prompt Injection with Structured Queries
prompt·提示注入攻击
一 铭16 小时前
AI领域新趋势:从提示(Prompt)工程到上下文(Context)工程
人工智能·语言模型·大模型·llm·prompt
悟乙己1 天前
通过Claude 生成图片的prompt集锦(一)
prompt·claude·李继刚
逻辑01 天前
Prompt:提示词工程
prompt
AIGC包拥它2 天前
提示技术系列——链式提示
人工智能·python·langchain·prompt
摸鱼仙人~2 天前
Prompt Engineering Guide — 提示工程全方位指南
prompt
非英杰不图2 天前
论文阅读:Align and Prompt (ALPRO 2021.12)
论文阅读·prompt
静心问道3 天前
Prompt Depth Anything:以提示方式驱动的Depth Anything用于实现4K分辨率下的精确米制深度估计
prompt
fightingwy3 天前
01 Prompt Enginering
prompt
cg501715 天前
OpenAI的Prompt工程
人工智能·prompt