AnswerDotAI / cold-compressLinks
Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of GPT-Fast, a simple, PyTorch-native generation codebase.
☆146Updated last year
Alternatives and similar repositories for cold-compress
Users that are interested in cold-compress are comparing it to the libraries listed below
Sorting:
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆89Updated 2 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆242Updated last week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆82Updated last year
- Code for studying the super weight in LLM☆119Updated 10 months ago
- ☆143Updated 7 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- The evaluation framework for training-free sparse attention in LLMs☆100Updated 3 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆155Updated 6 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆110Updated 6 months ago
- Explorations into some recent techniques surrounding speculative decoding☆288Updated 9 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆128Updated 10 months ago
- ☆127Updated last year
- ☆282Updated 2 months ago
- ☆148Updated 2 years ago
- ☆201Updated 10 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated 11 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆247Updated 8 months ago
- ☆129Updated 4 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆189Updated 3 months ago
- KV cache compression for high-throughput LLM inference☆141Updated 8 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆172Updated last year
- Fast and memory-efficient exact attention☆70Updated 7 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆215Updated last year
- ☆122Updated last year
- Experiments on speculative sampling with Llama models☆126Updated 2 years ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆117Updated last year
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆238Updated 9 months ago
- ☆52Updated 11 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆385Updated last year