00ffcc / chunkRWKV6
continous batching and parallel acceleration for RWKV6
☆23Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for chunkRWKV6
- ☆29Updated 5 months ago
- Here we will test various linear attention designs.☆56Updated 6 months ago
- ☆44Updated 4 months ago
- ☆97Updated 8 months ago
- [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Se…☆61Updated 6 months ago
- ☆22Updated 10 months ago
- Stick-breaking attention☆33Updated this week
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated 5 months ago
- ☆45Updated 9 months ago
- The this is the official implementation of "DAPE: Data-Adaptive Positional Encoding for Length Extrapolation"☆31Updated last month
- APPy (Annotated Parallelism for Python) enables users to annotate loops and tensor expressions in Python with compiler directives akin to…☆20Updated this week
- Triton implementation of FlashAttention2 that adds Custom Masks.☆74Updated 2 months ago
- ☆17Updated last year
- ☆95Updated last month
- Odysseus: Playground of LLM Sequence Parallelism☆55Updated 4 months ago
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆56Updated this week
- Transformers components but in Triton☆25Updated this week
- A 20M RWKV v6 can do nonogram☆11Updated 3 weeks ago
- An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆33Updated 5 months ago
- Triton implementation of Flash Attention2.0☆22Updated last year
- ☆46Updated last month
- Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆67Updated last week
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆24Updated 6 months ago
- Low-bit optimizers for PyTorch☆118Updated last year
- [EMNLP 2022] Official implementation of Transnormer in our EMNLP 2022 paper - The Devil in Linear Transformer☆54Updated last year
- [ICML'24 Oral] The official code of "DiJiang: Efficient Large Language Models through Compact Kernelization", a novel DCT-based linear at…☆98Updated 4 months ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆34Updated 7 months ago
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆30Updated 2 months ago
- ☆42Updated 11 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆53Updated last week