Popular repositories Loading

1. trnfft trnfft Public

   FFT and complex-valued tensor operations for AWS Trainium via NKI (cuFFT-equivalent) — Cooley-Tukey, Bluestein, STFT, ComplexTensor and complex NN layers.

   Python 1

2. trnblas trnblas Public

   BLAS Levels 1–3 for AWS Trainium via NKI (cuBLAS-equivalent) — GEMM with stationary-tile reuse, batched GEMM, TRSM, validated DF-MP2 for quantum chemistry.

   Python

3. trnrand trnrand Public

   Random number generation for AWS Trainium via NKI (cuRAND-equivalent) — Philox counter-based RNG, standard distributions, Sobol / Halton / Latin-hypercube quasi-random sequences for Monte Carlo and…

   HTML

4. trnsolver trnsolver Public

   Linear solvers and eigendecomposition for AWS Trainium via NKI (cuSOLVER-equivalent) — Jacobi eigh, Cholesky/LU/QR factorizations, CG/GMRES iterative solvers, Newton-Schulz inverse square root.

   Python

5. trnsci trnsci Public

   Scientific computing library suite for AWS Trainium via NKI — the cuFFT/cuBLAS/cuRAND/cuSOLVER/cuSPARSE/cuTENSOR equivalents for Neuron. Python-first, PyTorch fallback everywhere, Apache-2.0.

   Python

6. trnsparse trnsparse Public

   Sparse matrix operations for AWS Trainium via NKI (cuSPARSE-equivalent) — CSR/COO formats, SpMV and SpMM via gather-matmul-scatter, Schwarz integral screening for quantum chemistry.

   Python