facebookresearch / LayerSkip
Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024
☆284Updated last month
Alternatives and similar repositories for LayerSkip:
Users that are interested in LayerSkip are comparing it to the libraries listed below
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆195Updated 8 months ago
- The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".☆165Updated 2 weeks ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆313Updated 4 months ago
- ☆174Updated 4 months ago
- LLM KV cache compression made easy☆452Updated 3 weeks ago
- ☆196Updated 4 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆230Updated 2 months ago
- Manage scalable open LLM inference endpoints in Slurm clusters☆254Updated 9 months ago
- Simple extension on vLLM to help you speed up reasoning model without training.☆146Updated last month
- ☆82Updated this week
- Explorations into some recent techniques surrounding speculative decoding☆253Updated 3 months ago
- PyTorch implementation of models from the Zamba2 series.☆179Updated 2 months ago
- Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models☆229Updated 11 months ago
- EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language M…☆210Updated 5 months ago
- A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).☆215Updated last week
- A family of compressed models obtained via pruning and knowledge distillation☆333Updated 5 months ago
- Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".☆196Updated this week
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆217Updated 7 months ago
- Code for studying the super weight in LLM☆97Updated 4 months ago
- PyTorch building blocks for the OLMo ecosystem☆188Updated this week
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆151Updated 3 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆170Updated 2 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆447Updated 2 months ago
- Reproducible, flexible LLM evaluations☆186Updated 2 weeks ago
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆165Updated 3 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆238Updated this week
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆126Updated 8 months ago
- [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models☆212Updated last week
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆156Updated 9 months ago
- An extension of the nanoGPT repository for training small MOE models.☆115Updated last month