Matching a prefix is a trie walk. The grade is in the edge split, which cached tokens a running request pins, and an eviction loop that turns parents into leaves without ever freeing a slot twice.
an account raises the free count per topic
← Implement-from-Scratch Coding / 06
hardNewAnthropicOpenAIPerplexity
Implement a radix tree prefix cache: match, insert with edge splitting, request locks and LRU eviction of unlocked leaves.
Matching a prefix is a trie walk. The grade is in the edge split, which cached tokens a running request pins, and an eviction loop that turns parents into leaves without ever freeing a slot twice.
Updated Oct 2026 · Worked answers on inference mechanisms, with calculations, implementation details, and follow-up questions.
UP NEXT ON YOUR JOURNEY
Next in this trackImplement RoPE for a batched decode step where every row sits at a different position, and verify it against the full-sequence version.Next in this trackImplement INT4 packing with group scales and a dequantizing matmul, and test it against FP32 with odd K and a partial group.Next in this trackWrite a row-wise softmax kernel in Triton that stays correct when a row is longer than the block size, and test it.
DISCUSSION · 0
Nobody has commented on this answer. Add a correction or another way to work it.