hwang595 / Cuttlefish
The implementation for MLSys 2023 paper: "Cuttlefish: Low-rank Model Training without All The Tuning"
☆44Updated last year
Alternatives and similar repositories for Cuttlefish:
Users that are interested in Cuttlefish are comparing it to the libraries listed below
- ☆50Updated last year
- ☆102Updated last year
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆79Updated last year
- Linear Attention Sequence Parallelism (LASP)☆81Updated 10 months ago
- Repository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"☆115Updated last year
- Stick-breaking attention☆49Updated 3 weeks ago
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆47Updated last year
- ☆36Updated 7 months ago
- ☆141Updated last year
- The official code for Dropping Backward Propagation (DropBP)☆29Updated 5 months ago
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆30Updated 9 months ago
- Code associated with the paper **Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees**.☆28Updated last year
- ☆66Updated last month
- [ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity; Lu Yin*, Ajay Jaiswal*, Shiwei Liu, So…☆16Updated 10 months ago
- Code for "Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes"☆27Updated last year
- Low-Rank Llama Custom Training☆22Updated last year
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…☆48Updated 2 years ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆59Updated 2 months ago
- [ICLR 2025] Official PyTorch implementation of "Forgetting Transformer: Softmax Attention with a Forget Gate"☆87Updated this week
- ☆24Updated 4 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆60Updated 5 months ago
- Here we will test various linear attention designs.☆60Updated 11 months ago
- ☆81Updated last year
- Sparse Backpropagation for Mixture-of-Expert Training☆28Updated 9 months ago
- ☆122Updated last month
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆35Updated 7 months ago
- Official code for the paper "Attention as a Hypernetwork"☆25Updated 9 months ago
- Using FlexAttention to compute attention with different masking patterns☆43Updated 6 months ago
- [ICML2024 Spotlight] Fine-Tuning Pre-trained Large Language Models Sparsely☆22Updated 9 months ago
- ☆47Updated last year