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.
☆138Updated 11 months ago
Alternatives and similar repositories for cold-compress
Users that are interested in cold-compress are comparing it to the libraries listed below
Sorting:
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆151Updated 3 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆230Updated 8 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 10 months ago
- ☆136Updated 5 months ago
- Code for studying the super weight in LLM☆114Updated 7 months ago
- ☆199Updated 7 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆82Updated 2 weeks ago
- ☆268Updated 3 weeks ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆149Updated last month
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆244Updated 6 months ago
- ☆127Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆123Updated 7 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆61Updated 9 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆109Updated 4 months ago
- Explorations into some recent techniques surrounding speculative decoding☆275Updated 7 months ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆118Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆312Updated 6 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆238Updated last month
- The evaluation framework for training-free sparse attention in LLMs☆86Updated last month
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆362Updated 11 months ago
- ☆113Updated last year
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆228Updated 7 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆127Updated 8 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆167Updated last year
- Experiments on speculative sampling with Llama models☆128Updated 2 years ago
- Fast and memory-efficient exact attention☆68Updated 5 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆205Updated 8 months ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆134Updated this week
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆212Updated 11 months ago