kyegomez / Blockwise-Parallel-TransformerLinks
32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.
☆48Updated last year
Alternatives and similar repositories for Blockwise-Parallel-Transformer
Users that are interested in Blockwise-Parallel-Transformer are comparing it to the libraries listed below
Sorting:
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆97Updated 8 months ago
- Linear Attention Sequence Parallelism (LASP)☆83Updated last year
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆37Updated last year
- ☆54Updated 10 months ago
- ☆45Updated 3 months ago
- Here we will test various linear attention designs.☆58Updated last year
- ☆31Updated last year
- ☆103Updated last year
- An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆35Updated 11 months ago
- ☆46Updated last year
- ☆50Updated 7 months ago
- Low-Rank Llama Custom Training☆22Updated last year
- Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"☆17Updated 2 weeks ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- Transformers components but in Triton☆33Updated 3 weeks ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆41Updated last month
- Repository for CPU Kernel Generation for LLM Inference☆26Updated last year
- The implementation for MLSys 2023 paper: "Cuttlefish: Low-rank Model Training without All The Tuning"☆44Updated 2 years ago
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆30Updated 11 months ago
- Contextual Position Encoding but with some custom CUDA Kernels https://arxiv.org/abs/2405.18719☆22Updated 11 months ago
- GoldFinch and other hybrid transformer components☆45Updated 10 months ago
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- A repository for research on medium sized language models.☆76Updated last year
- Official implementation of the ICML 2024 paper RoSA (Robust Adaptation)☆42Updated last year
- Sparse Backpropagation for Mixture-of-Expert Training☆29Updated 11 months ago
- Pytorch implementation for "Compressed Context Memory For Online Language Model Interaction" (ICLR'24)☆60Updated last year
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆24Updated 11 months ago
- ☆22Updated last year
- Using FlexAttention to compute attention with different masking patterns☆43Updated 8 months ago
- Low-bit optimizers for PyTorch☆128Updated last year