Linear types + whitelisted destroyers = powers yet unimagined! May 14, 2024 — Also posted today: Layer-wise inferencing + batching: Small VRAM doesn't limit LLM throughput anymore, on how even a normal small computer can now run huge LLMs, much more quickly! Can you spot the problem in each of these comments? // Remember to update the database row with the new status. // Remember to remove(&cache, entityRef) before you destroy the entity! // Remember to fulfill this promise with the result of th...