kklemon / FlashPerceiver
Fast and memory efficient PyTorch implementation of the Perceiver with FlashAttention.
☆20Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for FlashPerceiver
- ☆32Updated 5 months ago
- Implementation of a framework for Gamengen in Pytorch☆90Updated 2 months ago
- ☆149Updated this week
- Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"☆161Updated 5 months ago
- ☆57Updated last week
- Code for "Re-Thinking Inverse Graphics With Large Language Models"; TMLR 2024☆59Updated 2 months ago
- ☆21Updated 5 months ago
- PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu☆39Updated 2 months ago
- σ-GPT: A New Approach to Autoregressive Models☆59Updated 3 months ago
- ☆53Updated 10 months ago
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆256Updated 2 weeks ago
- Text to Image Latent Diffusion using a Transformer core☆145Updated 2 months ago
- Implementation of the proposed Spline-Based Transformer from Disney Research☆76Updated last week
- Implementation of Dreamcraft3D, 3D content generation in Pytorch☆79Updated last year
- Implementation of LVSM, SOTA Large View Synthesis with Minimal 3d Inductive Bias, from Adobe Research☆76Updated last week
- faster parallel inference of mochi-1 video generation model☆73Updated last week
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆104Updated last month
- Explorations into the recently proposed Taylor Series Linear Attention☆90Updated 3 months ago
- Train VAE like a boss☆246Updated last month
- Exploration into the Firefly algorithm in Pytorch☆35Updated 2 months ago
- Transformer implementation for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"☆55Updated last month
- Simplified Masked Diffusion Language Model☆207Updated last week
- Patch convolution to avoid large GPU memory usage of Conv2D☆79Updated 5 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆187Updated this week
- One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation☆29Updated last month
- ☆24Updated 5 months ago
- Latent Diffusion Language Models☆67Updated last year
- Implementation of PyTorch: "GAMBA: MARRY GAUSSIAN SPLATTING WITH MAMBA FOR SINGLE-VIEW 3D RECONSTRUCTION"☆62Updated last week
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆112Updated 2 months ago
- RWKV-7: Surpassing GPT☆45Updated this week