Forward Pass Learning and Inference Library, for neural networks and general intelligence, Signal Propagation (sigprop)

Learn Triton by building FlashAttention from scratch — V2 kernels, persistent threads, mask DSL, profiling toolkit, bilingual docs

200 lines Flash Attention (only forward pass) in CUDA.

NumPy-only CNN implementation - Implements conv2d, ReLU, maxpool2d, flatten, dense, softmax and backpropagating from scratch

LSTM cell forward propagation implemented in Excel formulas across three linked worksheets.

Bounded forward-pass trace schema and persistence helpers for Crucible signal captures, layer trajectories, and decode telemetry.

Tap-plan and probe-contract library for selecting, bounding, and negotiating model-internal forward-pass observations.

Bumblebee, Axon, and Nx adapter layer for compiling Crucible tap plans into model runs, hooks, traces, and decode steering.

In this repository is a programm with a pretrained artificial neural network from Building AI. The network predicts the price of a cabin based on it's attributes.

Routing, gating, fusion, uncertainty, verifier, shared memory, and steering decision contracts over Crucible signal traces.

Canonical Elixir signal ontology for transformer forward-pass artifacts, tensor summaries, capabilities, and internal-control surfaces.

NumPy implementation of Word2Vec Skip-Gram with Negative Sampling. Trains word embeddings from raw text with manual forward pass, negative sampling loss, gradients, and SGD.