All posts on technology, daily life, and thoughts.
ActionPiece: Rethinking Action Tokenization Beyond Reconstruction Error, via Physical Ranking TL;DR — In autoregressive VLA (vision-language-action) models, the action…
DeepSeek-V4.1-Flash: A Multimodal MoE That Cuts the KV Cache to 1/4 While Raising Performance Further TL;DR. DeepSeek-V4.1-Flash, released by DeepSeek-AI, is a multimodal…
Open an LLM serving framework for the first time and you will probably go looking for the scheduler. But no amount of reading scheduler code answers the question that…
In chapter 1, what reached the scheduler was a 1-D int32 tensor on the CPU. While that token sequence grows into an answer, the system has to write down somewhere how far…
In chapter 2 a request became a ledger expressed by three lengths. Now there is one question left: with several requests waiting, what goes into this step, and how much…
In chapter 3 a request "secured its space". What that space actually is, is this chapter's subject. The KV cache is managed in pages. Yet open the pagetable that each…