SmerkyG / gptcore
Fast modular code to create and train cutting edge LLMs
☆66Updated 10 months ago
Alternatives and similar repositories for gptcore:
Users that are interested in gptcore are comparing it to the libraries listed below
- RWKV, in easy to read code☆71Updated this week
- ☆47Updated last week
- RWKV in nanoGPT style☆188Updated 9 months ago
- https://x.com/BlinkDL_AI/status/1884768989743882276☆27Updated last month
- RWKV-7: Surpassing GPT☆82Updated 4 months ago
- Griffin MQA + Hawk Linear RNN Hybrid☆85Updated 11 months ago
- supporting pytorch FSDP for optimizers☆80Updated 3 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆125Updated 3 months ago
- Normalized Transformer (nGPT)☆164Updated 4 months ago
- ☆49Updated last year
- FlashRNN - Fast RNN Kernels with I/O Awareness☆76Updated this week
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆47Updated last week
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆122Updated 7 months ago
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆31Updated 7 months ago
- QuIP quantization☆52Updated last year
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆224Updated last month
- GoldFinch and other hybrid transformer components☆45Updated 8 months ago
- A large-scale RWKV v6, v7(World, ARWKV, PRWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy o…☆33Updated last week
- Here we will test various linear attention designs.☆60Updated 11 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆108Updated 3 months ago
- JAX bindings for Flash Attention v2☆89Updated 8 months ago
- ☆32Updated last week
- ☆50Updated 5 months ago
- Token Omission Via Attention☆124Updated 5 months ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆87Updated 9 months ago
- Implementation of the Llama architecture with RLHF + Q-learning☆163Updated 2 months ago
- research impl of Native Sparse Attention (2502.11089)☆53Updated last month
- ☆79Updated 11 months ago
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆30Updated 3 months ago
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆148Updated 7 months ago