Skip to content
← Implement-from-Scratch Coding / 27
hardNewOpenAIAnthropicDatabricks

Implement a priority scheduler for a paged KV pool, with preemption and aging so low-priority requests cannot starve.

Strict priority starves the batch class at a sustained peak, and naive aging turns into a heap you must rebuild every step. The answer finds a key that never changes, decides who may evict whom, and tests the invariants a grader will break.

Updated Oct 2026 · Worked answers on inference mechanisms, with calculations, implementation details, and follow-up questions.

Strict priority starves the batch class at a sustained peak, and naive aging turns into a heap you must rebuild every step. The answer finds a key that never changes, decides who may evict whom, and tests the invariants a grader will break.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 213 remaining answers · $25

Every worked answer and derivation in all 12 topics, every concept page, the full practice-test bank, and every code drill’s edge-case tests and reference solution.

6 months · One payment · No auto-renewal

UP NEXT ON YOUR JOURNEY
Next in this trackImplement top-k and top-p sampling on the GPU for a batch of 256 over a 201,088-token vocabulary, without sorting.Next in this trackIn CUDA, count 1M MoE routing pairs per expert and scatter-add expert outputs back into tokens when one expert is hot.Next in this trackImplement a LoRA linear layer by hand, then decide whether to merge the adapter into a BF16 base and into an FP8 base.
DISCUSSION · 0

Nobody has commented on this answer. Add a correction or another way to work it.