OpenMOSE / RWKV-Infer
A large-scale RWKV v6, v7(World, ARWKV, PRWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy on docker. Supports true multi-batch generation and dynamic State switching. CUDA and Rocm Supported :)
☆33Updated last week
Alternatives and similar repositories for RWKV-Infer:
Users that are interested in RWKV-Infer are comparing it to the libraries listed below
- https://x.com/BlinkDL_AI/status/1884768989743882276☆27Updated 2 months ago
- Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton☆22Updated last week
- GoldFinch and other hybrid transformer components☆45Updated 8 months ago
- RWKV, in easy to read code☆71Updated last week
- ☆32Updated last week
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆31Updated 7 months ago
- Here we will test various linear attention designs.☆60Updated 11 months ago
- RWKV v5,v6 LoRA Trainer on Cuda and Rocm Platform. RWKV is a RNN with transformer-level LLM performance. It can be directly trained like …☆13Updated last year
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆50Updated last week
- A repository for research on medium sized language models.☆76Updated 10 months ago
- continous batching and parallel acceleration for RWKV6☆24Updated 9 months ago
- ☆22Updated 3 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆36Updated last year
- RWKV-7: Surpassing GPT☆82Updated 4 months ago
- Combining SOAP and MUON☆13Updated last month
- Reinforcement Learning Toolkit for RWKV.(v6,v7,ARWKV) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the…☆37Updated last week
- ☆47Updated last week
- This repo is based on https://github.com/jiaweizzhao/GaLore☆26Updated 6 months ago
- Triton Implementation of HyperAttention Algorithm☆47Updated last year
- RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…☆42Updated 2 weeks ago
- Fast modular code to create and train cutting edge LLMs☆66Updated 10 months ago
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated 9 months ago
- Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)☆26Updated 3 weeks ago
- Official Code Repository for the paper "Key-value memory in the brain"☆24Updated last month
- ☆32Updated 9 months ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆26Updated 11 months ago
- Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization☆15Updated 2 months ago
- A specialized RWKV-7 model for Othello(a.k.a. Reversi) that predicts legal moves, evaluates positions, and performs in-context search. It…☆39Updated 2 months ago
- ☆34Updated 8 months ago
- ☆52Updated 8 months ago