bojone / softtopkLinks
differentiable top-k operator
☆22Updated 8 months ago
Alternatives and similar repositories for softtopk
Users that are interested in softtopk are comparing it to the libraries listed below
Sorting:
- A torch-based implementation of K-Means and K-Means++☆17Updated 4 years ago
- Keras implement of Finite Scalar Quantization☆83Updated last year
- Triton implement of bi-directional (non-causal) linear attention☆55Updated 7 months ago
- Official Code for "Rethinking Diffusion Model in High Dimension"☆20Updated 4 months ago
- The official repo of continuous speculative decoding☆29Updated 5 months ago
- Self Reproduction Code of Paper "Reducing Transformer Key-Value Cache Size with Cross-Layer Attention (MIT CSAIL)☆18Updated last year
- IntLLaMA: A fast and light quantization solution for LLaMA☆18Updated 2 years ago
- [ICCV 2025] Preacher: Paper-to-Video Agentic System☆15Updated 3 weeks ago
- Benchmarking Attention Mechanism in Vision Transformers.☆18Updated 2 years ago
- [EVA ICLR'23; LARA ICML'22] Efficient attention mechanisms via control variates, random features, and importance sampling☆86Updated 2 years ago
- [ECCV 2024] This is the official implementation of "Stitched ViTs are Flexible Vision Backbones".☆28Updated last year
- This is a PyTorch implementation of the paperViP A Differentially Private Foundation Model for Computer Vision☆36Updated 2 years ago
- ☆45Updated 4 years ago
- ☆18Updated 8 months ago
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆132Updated last week
- An efficient multi-modal instruction-following data synthesis tool and the official implementation of Oasis https://arxiv.org/abs/2503.08…☆31Updated 3 months ago
- A repository for DenseSSMs☆88Updated last year
- Official PyTorch implementation of "Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets" (ICLR 2023 notable top 25%)☆24Updated last year
- The official implementation of the paper "Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation"☆20Updated 9 months ago
- [ACL 2023] PuMer: Pruning and Merging Tokens for Efficient Vision Language Models☆33Updated 11 months ago
- LLaVA combines with Magvit Image tokenizer, training MLLM without an Vision Encoder. Unifying image understanding and generation.☆37Updated last year
- Mixture of Attention Heads☆49Updated 2 years ago
- WeGeFT: Weight‑Generative Fine‑Tuning for Multi‑Faceted Efficient Adaptation of Large Models