pbelcak / fastfeedforwardLinks
A repository for log-time feedforward networks
☆223Updated last year
Alternatives and similar repositories for fastfeedforward
Users that are interested in fastfeedforward are comparing it to the libraries listed below
Sorting:
- The AdEMAMix Optimizer: Better, Faster, Older.☆185Updated 11 months ago
- The repository for the code of the UltraFastBERT paper☆517Updated last year
- Efficient optimizers☆256Updated 3 weeks ago
- ☆307Updated last year
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆229Updated 11 months ago
- Annotated version of the Mamba paper☆488Updated last year
- Accelerated First Order Parallel Associative Scan☆187Updated last year
- Fast, Modern, and Low Precision PyTorch Optimizers☆108Updated 3 weeks ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆127Updated last year
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆220Updated last year
- supporting pytorch FSDP for optimizers☆84Updated 8 months ago
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆124Updated last year
- ☆53Updated last year
- ☆118Updated last year
- FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores☆327Updated 7 months ago
- ☆101Updated last month
- ☆82Updated last year
- Understand and test language model architectures on synthetic tasks.☆222Updated last month
- Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.☆379Updated last year
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆289Updated 2 months ago
- Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"☆559Updated 7 months ago
- Load compute kernels from the Hub☆244Updated this week
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆241Updated 2 months ago
- Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch☆119Updated 9 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆101Updated 8 months ago
- Griffin MQA + Hawk Linear RNN Hybrid☆88Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆153Updated 2 months ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated 10 months ago
- Implementation of the Llama architecture with RLHF + Q-learning☆166Updated 6 months ago
- ☆194Updated 2 weeks ago