kklemon / FlashPerceiverLinks
Fast and memory efficient PyTorch implementation of the Perceiver with FlashAttention.
☆26Updated 7 months ago
Alternatives and similar repositories for FlashPerceiver
Users that are interested in FlashPerceiver are comparing it to the libraries listed below
Sorting:
- Focused on fast experimentation and simplicity☆74Updated 6 months ago
- ☆53Updated last year
- ☆22Updated last month
- σ-GPT: A New Approach to Autoregressive Models☆65Updated 10 months ago
- ☆65Updated last year
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated last month
- Explorations into the recently proposed Taylor Series Linear Attention☆99Updated 10 months ago
- GoldFinch and other hybrid transformer components☆45Updated 11 months ago
- Official implementation of the paper: "ZClip: Adaptive Spike Mitigation for LLM Pre-Training".☆127Updated 3 weeks ago
- Esoteric Language Models☆77Updated last week
- ☆32Updated last year
- Code accompanying the paper "Generalized Interpolating Discrete Diffusion"☆85Updated 2 weeks ago
- ☆34Updated 9 months ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆56Updated last year
- ☆27Updated last year
- ☆32Updated last year
- Implementation of the proposed Spline-Based Transformer from Disney Research☆97Updated 7 months ago
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆37Updated 4 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆126Updated 6 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 2 weeks ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆102Updated 9 months ago
- RWKV-7: Surpassing GPT☆91Updated 7 months ago
- ☆70Updated 9 months ago
- ☆31Updated 7 months ago
- A basic pure pytorch implementation of flash attention☆16Updated 7 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆127Updated last year
- ☆36Updated 2 months ago
- Implementation of an Attention layer where each head can attend to more than just one token, using coordinate descent to pick topk☆46Updated last year
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆52Updated 3 months ago
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 5 months ago