OpenMOSE / RWKV-InferLinks
A large-scale RWKV v6, v7(World, PRWKV, Hybrid-RWKV) 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 :)
☆38Updated 3 weeks ago
Alternatives and similar repositories for RWKV-Infer
Users that are interested in RWKV-Infer are comparing it to the libraries listed below
Sorting:
- RWKV-X is a Linear Complexity Hybrid Language Model based on the RWKV architecture, integrating Sparse Attention to improve the model's l…☆39Updated last month
- Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton☆33Updated last week
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated last month
- ☆36Updated last month
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆32Updated 10 months ago
- GoldFinch and other hybrid transformer components☆45Updated 11 months ago
- RWKV-7: Surpassing GPT☆91Updated 7 months ago
- Reinforcement Learning Toolkit for RWKV.(v6,v7,ARWKV) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the…☆44Updated last month
- ☆18Updated 5 months ago
- RWKV, in easy to read code☆72Updated 3 months ago
- This project is to extend RWKV LM's capabilities including sequence classification/embedding/peft/cross encoder/bi encoder/multi modaliti…☆10Updated 10 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
- Fast modular code to create and train cutting edge LLMs☆67Updated last year
- RWKV-LM-V7(https://github.com/BlinkDL/RWKV-LM) Under Lightning Framework☆31Updated this week
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 2 weeks ago
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆98Updated 8 months ago
- Here we will test various linear attention designs.☆59Updated last year
- The WorldRWKV project aims to implement training and inference across various modalities using the RWKV7 architecture. By leveraging diff…☆50Updated last month
- A repository for research on medium sized language models.☆76Updated last year
- A specialized RWKV-7 model for Othello(a.k.a. Reversi) that predicts legal moves, evaluates positions, and performs in-context search. It…☆41Updated 5 months ago
- ☆22Updated this week
- BlackGoose Rimer: RWKV as a Superior Architecture for Large-Scale Time Series Modeling☆24Updated last week
- RWKV centralised docs for the community☆27Updated 2 months ago
- QuIP quantization☆54Updated last year
- continous batching and parallel acceleration for RWKV6☆24Updated 11 months ago
- MiSS is a novel PEFT method that features a low-rank structure but introduces a new update mechanism distinct from LoRA, achieving an exc…☆19Updated this week
- Repository for the Q-Filters method (https://arxiv.org/pdf/2503.02812)☆33Updated 3 months ago
- ☆23Updated 5 months ago
- State tuning tunes the state☆33Updated 4 months ago
- DPO, but faster 🚀☆43Updated 6 months ago