layernorm

Here are 16 public repositories matching this topic...

metaSATOKEN / manifold_topology_experiment

Topology and geometry of Transformer hidden states via persistent homology. The manifold is a 1D arc (PC1=norm, r=0.999), not a torus or sphere. PC2=position, PC3=surprisal+POS. Validated up to 40B.

reproducible-research pytorch open-science transformer pca persistent-homology hidden-states probing betti-numbers layernorm mechanistic-interpretability manifold-topology

Updated Apr 15, 2026
Python

iamjadhav / enpm809k

Star

Fundamentals of Artificial Intelligence and Deep Learning Frameworks

deep-neural-networks deep-learning optimization svm cross-validation pytorch knn backpropagation stochastic-gradient-descent softmax fully-connected-network batchnormalization layernorm

Updated Nov 2, 2022
Jupyter Notebook

szl-holdings / szl-governed-norm

Star

Governed RMSNorm/LayerNorm universal kernel — correctness-verified normalization with optional SHA3-256 hash-chained provenance receipts. Mirrors HF SZLHOLDINGS/szl-governed-norm. Λ = Conjecture 1 (advisory) · Apache-2.0.

kernel pytorch provenance governance huggingface layernorm dsse rmsnorm agentic-ai defense-tech governed-ai szl-holdings governed-inference doctrine-v11 kernel-hub

Updated Aug 8, 2026
Python

metaSATOKEN / geometric_phase_extraction

Star

Geometric phase structure in Transformer hidden states. LayerNorm placement predicts manifold geometry — 6x difference in PCA concentration. 9 models, 13 experiments.

reproducible-research transformers pytorch open-science pca hidden-states ai-research layernorm mechanistic-interpretability manifold-geometry phase-extraction

Updated Mar 30, 2026
Python

lokeshyarlagadda473 / triton-layernorm

Star

Fused LayerNorm (forward + backward) in Triton, benchmarked against PyTorch

kernel deep-learning gpu cuda pytorch triton layernorm

Updated Aug 9, 2026
Python

Khanz9664 / layernorm

Sponsor

Star

Pure C implementation of Layer Normalization with learnable γ and β parameters—built from scratch without ML frameworks or autograd.

c nlp machine-learning transformers layer-normalization transformer-architecture layernorm llm

Updated Jul 4, 2026
C

rikhil-amonkar / pytorch-cpp-layernorm-accelerator

Star

Implemented a custom LayerNorm forward and backward pass extension in C++ using LibTorch and validated numerical equivalence with PyTorch.

python machine-learning deep-neural-networks ai deep-learning cpp numpy pytorch artificial-intelligence tensors libtorch layernorm

Updated Jan 24, 2026
C++

rushhan / WGAN-with-Feedback-Cross-Attention-LayerNorm

Star

WGAN with feedback from discriminator& LayerNorm instead of BatchNorm

feedback pytorch attention wgan wasserstein-gan attention-is-all-you-need pytorch-implementation wasserstein-distance layernorm

Updated Sep 12, 2020
Python

JonSnow1807 / Fused-LayerNorm-CUDA-Operator

Star

Fused normalisation CUDA kernels for PyTorch — residual-add+LayerNorm/RMSNorm, fp8 outputs, fast deterministic backward, torch.compile-native, with reproducible A100/H100 benchmarks

deep-learning cuda pytorch gpu-optimization kernel-fusion layernorm cuda-kernel