2.2 KiB
Speculation
Speculative decoding, assisted generation, Medusa, and others are a few different names for the same idea. The idea is to generate tokens before the large model actually runs, and only check if those tokens where valid.
So you are making more computations on your LLM, but if you are correct you produce 1, 2, 3 etc.. tokens on a single LLM pass. Since LLMs are usually memory bound (and not compute bound), provided your guesses are correct enough, this is a 2-3x faster inference (It can be much more for code oriented tasks for instance).
You can check a more detailed explanation.
Text-generation inference supports 2 main speculative methods:
- Medusa
- N-gram
Medusa
Medusa is a simple method to create many tokens in a single pass using fine-tuned LM heads in addition to your existing models.
You can check a few existing fine-tunes for popular models:
- text-generation-inference/gemma-7b-it-medusa
- text-generation-inference/Mixtral-8x7B-Instruct-v0.1-medusa
- text-generation-inference/Mistral-7B-Instruct-v0.2-medusa
In order to create your own medusa heads for your own finetune, you should check own the original medusa repo. https://github.com/FasterDecoding/Medusa
In order to use medusa models in TGI, simply point to a medusa enabled model, and everything will load automatically.
N-gram
If you don't have a medusa model, or don't have the resource to fine-tune, you can try to use n-gram.
Ngram works by trying to find in the previous sequence existing tokens that match, and use those as speculation.
This is an extremely simple method, which works best for code, or highly repetitive text. This might not be beneficial, if the speculation misses too much.
In order to enable n-gram speculation simply use
--speculate 2 in your flags.