Alternatives and similar repositories for einsum-search:

Users that are interested in einsum-search are comparing it to the libraries listed below

• shikaiqiu / compute-better-spent
  ☆52Updated 5 months ago
• srush / mamba-scans
  Blog post
  ☆17Updated last year
• jopetty / word-problem
  Experiments on the impact of depth in transformers and SSMs.
  ☆23Updated 3 months ago
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆47Updated last year
• vvvm23 / mamba-jax
  Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX
  ☆82Updated last year
• google-deepmind / spectral_ssm
  ☆31Updated 10 months ago
• michaelsdr / sinkformers
  Transformers with doubly stochastic attention
  ☆45Updated 2 years ago
• ruke1ire / RTF
  A State-Space Model with Rational Transfer Function Representation.
  ☆77Updated 9 months ago
• lxxue / prefix_sum
  A PyTorch wrapper of parallel exclusive scan in CUDA
  ☆10Updated last year
• maximzubkov / fft-scan
  Efficient PScan implementation in PyTorch
  ☆16Updated last year
• EleutherAI / rnngineering
  Engineering the state of RNN language models (Mamba, RWKV, etc.)
  ☆32Updated 9 months ago
• sustcsonglin / gated_linear_attention_layer
  ☆33Updated last year
• radarFudan / mamba-minimal-jax
  ☆30Updated 3 months ago
• necludov / action-matching
  Implementation of Action Matching for the Schrödinger equation
  ☆24Updated last year
• srush / tangent
  Source-to-Source Debuggable Derivatives in Pure Python
  ☆15Updated last year
• smonsays / hypernetwork-attention
  Official code for the paper "Attention as a Hypernetwork"
  ☆24Updated 8 months ago
• srush / mamba-primer
  ☆37Updated 10 months ago
• tml-epfl / why-weight-decay
  Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]
  ☆60Updated 5 months ago
• bhoov / energy-transformer-jax
  The Energy Transformer block, in JAX
  ☆56Updated last year
• sustcsonglin / mamba-triton
  ☆47Updated last year
• glassroom / heinsen_attention
  Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)
  ☆24Updated 8 months ago
• GallagherCommaJack / modulax
  ☆16Updated 6 months ago
• GFNOrg / GFlowNet-EM
  Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.
  ☆41Updated last year
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆76Updated last year
• ejmichaud / grokking-squared
  ☆24Updated 2 years ago
• berlino / seq_icl
  ☆51Updated 9 months ago
• abhishekpanigrahi1996 / transformer_in_transformer
  ☆44Updated last year
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆58Updated last year
• ermongroup / fast_feedforward_computation
  Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021
  ☆27Updated 3 years ago