AnswerDotAI / cold-compress
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.
☆122Updated 7 months ago
Alternatives and similar repositories for cold-compress:
Users that are interested in cold-compress are comparing it to the libraries listed below
- ☆122Updated last month
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆235Updated last month
- ☆125Updated last year
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆148Updated 2 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆226Updated 2 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆71Updated 6 months ago
- ☆42Updated last year
- The official repo for "LLoCo: Learning Long Contexts Offline"☆116Updated 9 months ago
- Explorations into some recent techniques surrounding speculative decoding☆250Updated 3 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆158Updated 8 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆209Updated 4 months ago
- Code for studying the super weight in LLM☆94Updated 3 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆59Updated 2 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆207Updated 7 months ago
- ☆195Updated 3 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆90Updated last week
- ☆233Updated 11 months ago
- 🔥 A minimal training framework for scaling FLA models☆92Updated last week
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆92Updated last year
- The HELMET Benchmark☆123Updated 2 weeks ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆337Updated 7 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆111Updated 3 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆94Updated last month
- LLM KV cache compression made easy☆444Updated last week
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆59Updated 5 months ago
- ☆220Updated 9 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆125Updated 3 months ago
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆91Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆281Updated 2 months ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆224Updated last month