Q: Did you just way over-optimize for a specific CPU and tokenizer? How is it so fast?
No, I way over-optimized for every combination of these! The results are very consistent across CPUs (modern x86 and ARM), and across specific tokenizers.
The major improvements are in optimizing heavily an implementation that usually is outsourced to a Regex engine (pretokenization) using SIMD, minimizing branching and other tricks, as well as heavily optimizing caching of pretoken mappings (if a word has been seen before, look it up its encoded tokens efficiently). Caching is a very hard problem in this domain since the cache grows very quickly, and pretoken distributions are very long-tailed.
Finally, interactions with Python are minimized, and threads have minimal interactions with each other.
Practically I would need to wait for hugging face models to adopt this? My harness tokenizer is just an estimate since the model tokenizes on my api calls?
Cool stuff. From my understanding, this is less valuable at inference time and more useful when running offline pre-training data prep.
When tokenizing terabytes of text for your training corpus, the speedup here is probably doing real work in saving you time (and money?). You get a faster iteration cycle when figuring out and adjusting your datasets.
For the lazy among us (not me of course), is there a small number of core techniques which enabled this for even a single architecture and single CPU core?
Can I say this seems to be fantastic work. I cloned your repo earlier today after seeing it on the tokenization discord. I know everyone in the tokenization community wants to absorb the lessons of how you got such a speedup. The caching and replacing the regex for pretokenization seem like generally useful ideas.
And screw all the 0.1% haters on here, this is great stuff.
Tokenization is one of the most under appreciated and under optimized part of the agentic stack- not sure if this is truly production grade, and applicable across all hardware+stack combo but this for sure can help inspire a lot of that work. Good work!
Spectacular... Reminds me of the SimdJson algorithm in terms of jaw dropping nearly unbelievable speeds through creative programming. I hope this code get popular, as it will save tons of electricity, money, CO2, etc.
Have you considered publishing a rust crate as well? (If not, I volunteer.)
37 comments
[ 5.0 ms ] story [ 960 ms ] threadQ: Did you just way over-optimize for a specific CPU and tokenizer? How is it so fast? No, I way over-optimized for every combination of these! The results are very consistent across CPUs (modern x86 and ARM), and across specific tokenizers.
The major improvements are in optimizing heavily an implementation that usually is outsourced to a Regex engine (pretokenization) using SIMD, minimizing branching and other tricks, as well as heavily optimizing caching of pretoken mappings (if a word has been seen before, look it up its encoded tokens efficiently). Caching is a very hard problem in this domain since the cache grows very quickly, and pretoken distributions are very long-tailed.
Finally, interactions with Python are minimized, and threads have minimal interactions with each other.
Presumably there's a host of applications that just need to tokenize, though, and this would be great for those!
When tokenizing terabytes of text for your training corpus, the speedup here is probably doing real work in saving you time (and money?). You get a faster iteration cycle when figuring out and adjusting your datasets.
It will be nicer if the README focuses more on per-core performance.
About the actual algorithm - will something like matching in a perfect hash table help?
And screw all the 0.1% haters on here, this is great stuff.
Have you considered publishing a rust crate as well? (If not, I volunteer.)