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:
- Triton-based implementation of Sparse Mixture of Experts.☆239Updated 3 weeks ago
- Code for studying the super weight in LLM☆117Updated 9 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆87Updated 2 months ago
- Explorations into some recent techniques surrounding speculative decoding☆285Updated 8 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆82Updated last year
- ☆142Updated 7 months ago
- ☆202Updated 9 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆155Updated 5 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆245Updated 7 months ago
- The evaluation framework for training-free sparse attention in LLMs☆93Updated 2 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆109Updated 5 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆185Updated 3 months ago
- ☆279Updated 2 months ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆235Updated 9 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆241Updated 3 months ago
- ☆128Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆126Updated 9 months ago
- ☆118Updated last year
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆140Updated this week
- The official repo for "LLoCo: Learning Long Contexts Offline"☆116Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆216Updated last year
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆381Updated last year
- ☆47Updated last year
- Fast and memory-efficient exact attention☆69Updated 6 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆170Updated last year
- 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
- Experiments on speculative sampling with Llama models☆128Updated 2 years ago
- ☆149Updated 2 years ago
- KV cache compression for high-throughput LLM inference☆138Updated 7 months ago