Bruce Lee's Notes

Systems, programming, and engineering practice

Transposed Convolution Weights: The Shape Is Honest, but Memory Speaks Another Dialect

Derive slices from actual weight storage, not just a logical dimension order.

Series contents · Operators and Layouts · 阅读中文版 The first time this error appears, it is tempting to suspect kernel reversal, stride, or padding: one group works beautifully, but enabling grouping ......

Grouped Convolution: Once You Slice the Cake, Slice the Labels Too

Split input and weight groups while carrying their quantization metadata with them.

Series contents · Operators and Layouts · 阅读中文版 “Ordinary convolution already works. Surely grouped convolution just needs one more parameter?” That sentence is about as dangerous as “this is only ......

The Importer Got Clever Too Soon: Algebraic Optimization before Quantization Metadata

Understand the interaction between algebraic rewrite order, metadata matching, and constants.

Series contents · Numerics and Quantization · 阅读中文版 “A constant divided by a tensor—wouldn’t a scaled reciprocal be more efficient?” The enthusiastic importer tidies the algebra as soon as the mode......

Floating Point Passes, Quantization Fails: A Rewrite Gives the Output the Input’s Identity

Treat the rewritten result type as both a container and a numerical contract.

Series contents · Numerics and Quantization · 阅读中文版 “The floating-point model compiles. The quantized one cannot get through the first stage.” Someone starts suspecting backend integer instructions......

Epsilon Was Nonzero—Until It Nearly Vanished in the Integer Domain

Follow epsilon, squares, and reciprocal square roots through normalization range planning.

Series contents · Numerics and Quantization · 阅读中文版 “We add epsilon to prevent division by zero.” Everyone relaxes. Then someone looks at the quantized constant and asks, “What value does it have a......