Byte Pair Encoding
Subword tokenization algorithm for vocabularies
Episodes
-
#6011: Inside LLM Inference: Prefill, Decode, and the KV CacheOne 8K-token sequence on a 13B model eats 6.7GB of KV cache—while the weights are only 26GB. Here's what actually happens per request. -
#2982: Why Your TTS Model Nails "Shabbat" but Not "Keren HishtalmutWhy multilingual TTS models handle loanwords but fail at niche vocabulary — and what you can do about it. -
#2076: Is Pure NLP Dead? The Hidden Scaffolding of AIModern AI didn't appear from nowhere. Discover how decades of linguistic rules and statistical models built the foundation for today's LLMs.