Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024
☆377Jul 20, 2026Updated 2 weeks ago
Alternatives and similar repositories for LayerSkip
Users that are interested in LayerSkip are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆82Jun 14, 2024Updated 2 years ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆67Sep 28, 2024Updated last year
- Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".☆929Oct 28, 2024Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆230Feb 13, 2025Updated last year
- MEXMA: Token-level objectives improve sentence representations☆44Jan 6, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICML 2024] CLLMs: Consistency Large Language Models☆415Nov 16, 2024Updated last year
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆206Jul 17, 2024Updated 2 years ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,500Feb 20, 2026Updated 5 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆540Feb 10, 2025Updated last year
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,762Jun 25, 2024Updated 2 years ago
- Cascade Speculative Drafting☆33Apr 2, 2024Updated 2 years ago
- Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.☆4,763Jul 18, 2025Updated last year
- A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).☆381Jun 25, 2026Updated last month
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆220Mar 5, 2026Updated 5 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Explorations into some recent techniques surrounding speculative decoding☆307Dec 22, 2024Updated last year
- [ICLR26] Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs☆33Dec 9, 2025Updated 8 months ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆311May 1, 2025Updated last year
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆73Jun 26, 2024Updated 2 years ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆261Jan 31, 2025Updated last year
- ☆226Jan 23, 2025Updated last year
- LLM KV cache compression made easy☆1,163Updated this week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆156Dec 4, 2024Updated last year
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation☆32Nov 16, 2024Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,225Apr 8, 2026Updated 4 months ago
- GRadient-INformed MoE☆265Sep 25, 2024Updated last year
- ☆15Apr 11, 2024Updated 2 years ago
- Simple speculative decoding technique, integrated in vLLM and transformers☆612Aug 23, 2024Updated last year
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆379Dec 12, 2024Updated last year
- MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.☆1,456Apr 30, 2026Updated 3 months ago
- A family of compressed models obtained via pruning and knowledge distillation☆384Nov 6, 2025Updated 9 months ago
- scalable and robust tree-based speculative decoding algorithm☆377Jan 28, 2025Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,340Mar 6, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆24Nov 21, 2024Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆92Jul 17, 2025Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,610Jul 17, 2025Updated last year
- ☆63May 19, 2025Updated last year
- Official repository for the paper "NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks". This rep…☆62Oct 31, 2024Updated last year
- [ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization☆724Aug 13, 2024Updated last year
- Generative Representational Instruction Tuning☆697Jun 25, 2025Updated last year