OpenMOSE / RWKV-Infer
A large-scale RWKV v6, v7(World, ARWKV) 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 :)
☆31Updated last week
Alternatives and similar repositories for RWKV-Infer:
Users that are interested in RWKV-Infer are comparing it to the libraries listed below
- GoldFinch and other hybrid transformer components☆44Updated 7 months ago
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆31Updated 6 months ago
- Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton☆18Updated this week
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆96Updated 5 months ago
- RWKV-7: Surpassing GPT☆79Updated 3 months ago
- Here we will test various linear attention designs.☆59Updated 10 months ago
- A repository for research on medium sized language models.☆76Updated 9 months ago
- continous batching and parallel acceleration for RWKV6☆24Updated 8 months ago
- RWKV, in easy to read code☆68Updated 3 months ago
- ☆50Updated 7 months ago
- Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization☆14Updated last month
- Reinforcement Learning Toolkit for RWKV.(v6,v7,ARWKV) Distillation,SFT,RLHF(DPO,ORPO), infinite context training, Aligning. Exploring the…☆31Updated this week
- Fast modular code to create and train cutting edge LLMs☆65Updated 9 months ago
- ☆30Updated 9 months ago
- ☆13Updated 2 months ago
- ☆47Updated last year
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆35Updated last year
- ☆21Updated 2 months ago
- DPO, but faster 🚀☆40Updated 2 months ago
- Triton Implementation of HyperAttention Algorithm☆47Updated last year
- 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 …☆12Updated 11 months ago
- QuIP quantization☆51Updated 11 months ago
- ☆13Updated this week
- Awesome Triton Resources☆20Updated 2 months ago
- Official Code Repository for the paper "Key-value memory in the brain"☆23Updated this week
- Linear Attention Sequence Parallelism (LASP)☆79Updated 8 months ago
- HGRN2: Gated Linear RNNs with State Expansion☆53Updated 6 months ago
- Evaluating LLMs with Dynamic Data☆75Updated 2 weeks ago