Recently, while implementing the paper Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting, I encountered a question about its use of Cross Entropy Loss to align the probability distributions of the draft model and the target model. Why not use KL Divergence instead?
Read More »Differences and Comparison Between KL Divergence and Cross Entropy
Many of the inference acceleration techniques I have studied, such as Speculative Decoding, predominantly use a threshold for the confidence scores of the draft model. This threshold determines how many draft tokens should be decoded before passing them to the target model for verification, thereby reducing the extra computational cost when the draft model operates with low confidence.
Read More »Using The Target Model's Confidence Threshold To Decide Whether To Enable Speculative Decoding
Recently, I attempted to implement various speculative decoding acceleration methods. HuggingFace's transformers library also provides a corresponding acceleration feature called assistant_model. Today, let me take this opportunity to document it.
Over the past week, I dedicated some time to reproducing the Self-Speculative Decoding mechanism based on the ideas from the paper Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding, implementing the following modules:
In self-speculative decoding, since our draft model is derived from part of the target model’s network, finding an optimal 'Layer Skip Strategy' is crucial. We need to skip enough layers to achieve meaningful speedup while ensuring the draft model’s speculative decoding is good enough to avoid frequent rejection by the target model.
Today’s implementation focuses on optimizing my previously implemented LayerSkip model using the Bayesian optimization framework Optuna, to determine which layers to skip.
Read More »Optimizing LayerSkip Models with Bayesian Search for an Effective Layer Skipping Strategy
Self-Speculative Decoding is a variant of Speculative Decoding. The original Speculative Decoding method uses a draft model to optimize the inference of the target model. The draft model, which is typically distilled from the target model, offers similar output quality but with several times faster inference speed.
Read More »Self-Speculative Decoding Implementation: LayerSkip Transformer
Speculative Decoding is an extremely practical inference acceleration technique that enables a small model (draft model) to rapidly decode multiple tokens and retain the probability distribution of this process. Then, the larger target model, which we aim to accelerate, predicts the next token based on this draft. For each token position, the draft model’s probability distributions are computed and validated using the target model's probabilities, accepting the tokens decoded by the draft model if they are deemed sufficiently reliable.
Read More »Speculative Decoding Implementation Note (with Simple Experimental Results)
When we use large language models for generative tasks, particularly in auto-regressive tasks, the model essentially performs a massive classification task. The classification targets are the tokens in our vocabulary, which are the smallest building blocks that make up words.
If we want to use greedy decoding, we can simply take the maximum value of the logits in the final layer of the model's decoding layer. However, if we want to introduce diversity and some level of randomness in the model's output, we have several parameters we can adjust to turn the logits into a probability distribution.
Read More »A Note Of Large Language Model Decode Sampling
In auto-regressive model decoding, if we need to decode K tokens, we must go through the process K times, which is the current bottleneck in the inference time of large language models.
Read More »[Paper Reading] Fast Inference from Transformers via Speculative Decoding
