Alternatives and similar repositories for softtopk

Users that are interested in softtopk are comparing it to the libraries listed below

• alihassanijr / TorchKMeans
  A torch-based implementation of K-Means and K-Means++
  ☆17Updated 4 years ago
• HubHop / vit-attention-benchmark
  Benchmarking Attention Mechanism in Vision Transformers.
  ☆18Updated 2 years ago
• JerryYin777 / Cross-Layer-Attention
  Self Reproduction Code of Paper "Reducing Transformer Key-Value Cache Size with Cross-Layer Attention (MIT CSAIL)
  ☆17Updated last year
• bojone / FSQ
  Keras implement of Finite Scalar Quantization
  ☆77Updated last year
• HKUNLP / efficient-attention
  [EVA ICLR'23; LARA ICML'22] Efficient attention mechanisms via control variates, random features, and importance sampling
  ☆86Updated 2 years ago
• HelmholtzAI-FZJ / flex_gen
  ☆17Updated 6 months ago
• fla-org / flash-bidirectional-linear-attention
  Triton implement of bi-directional (non-causal) linear attention
  ☆52Updated 5 months ago
• yyyyychen / LowMemoryBP
  The official implementation of the paper "Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation"
  ☆20Updated 7 months ago
• megvii-research / IntLLaMA
  IntLLaMA: A fast and light quantization solution for LLaMA
  ☆18Updated last year
• savadikarc / wegeft
  WeGeFT: Weight‑Generative Fine‑Tuning for Multi‑Faceted Efficient Adaptation of Large Models
  ☆20Updated last week
• WailordHe / DenseSSM
  A repository for DenseSSMs
  ☆87Updated last year
• Letian2003 / MM_INF
  An efficient multi-modal instruction-following data synthesis tool and the official implementation of Oasis https://arxiv.org/abs/2503.08…
  ☆14Updated last month
• yikangshen / MoA
  Mixture of Attention Heads
  ☆47Updated 2 years ago
• zhixuan-lin / forgetting-transformer
  [ICLR 2025] Official PyTorch implementation of "Forgetting Transformer: Softmax Attention with a Forget Gate"
  ☆116Updated 2 weeks ago
• yangjackie / Topics-on-diffusion-generative-models
  ☆26Updated last week
• OpenSparseLLMs / Open-Pandora
  Open-Pandora: On-the-fly Control Video Generation
  ☆34Updated 7 months ago
• davidsvy / cosformer-pytorch
  Unofficial PyTorch implementation of the paper "cosFormer: Rethinking Softmax In Attention".
  ☆44Updated 3 years ago
• shaoshitong / diffusion-model-learning
  Document the demo and a series of documents for learning the diffusion model.
  ☆39Updated 2 years ago
• TencentARC / pi-Tuning
  Official code for "pi-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation", ICML 2023.
  ☆33Updated last year
• BBuf / flash-rwkv
  ☆31Updated last year
• CownowAn / DaSS
  Official PyTorch implementation of "Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets" (ICLR 2023 notable top 25%)
  ☆24Updated last year
• facebookresearch / ViP-MAE
  This is a PyTorch implementation of the paperViP A Differentially Private Foundation Model for Computer Vision
  ☆36Updated 2 years ago
• lucasjinreal / LLaVA-Magvit2
  LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.
  ☆37Updated last year
• csarron / PuMer
  [ACL 2023] PuMer: Pruning and Merging Tokens for Efficient Vision Language Models
  ☆32Updated 9 months ago
• kyegomez / Blockwise-Parallel-Transformer
  32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.
  ☆48Updated 2 years ago
• li-plus / flash-preference
  Accelerate LLM preference tuning via prefix sharing with a single line of code
  ☆42Updated 2 weeks ago
• 360CVGroup / Inner-Adaptor-Architecture
  LMM solved catastrophic forgetting, AAAI2025
  ☆44Updated 3 months ago
• bojone / tiger
  A Tight-fisted Optimizer
  ☆48Updated 2 years ago
• berlino / gated_linear_attention
  ☆105Updated last year
• ziplab / SN-Netv2
  [ECCV 2024] This is the official implementation of "Stitched ViTs are Flexible Vision Backbones".
  ☆27Updated last year