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.
☆153Aug 9, 2024Updated 2 years ago
Alternatives and similar repositories for cold-compress
Users that are interested in cold-compress are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆44Aug 14, 2024Updated 2 years ago
- ☆22Apr 17, 2025Updated last year
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆51Jun 19, 2024Updated 2 years ago
- ☆336Jul 10, 2025Updated last year
- The Official Implementation of Ada-KV [NeurIPS 2025]☆143Nov 26, 2025Updated 11 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Algorithm-System Co-design: accurate and efficient 2-bit KV cache quantization for LLM Inference.☆23May 20, 2026Updated 5 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆414Jul 10, 2025Updated last year
- KV cache compression for high-throughput LLM inference☆163Feb 5, 2025Updated last year
- ☆16Jun 4, 2024Updated 2 years ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,232Oct 10, 2026Updated 3 weeks ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆168Feb 20, 2025Updated last year
- Tool to apply Legal Matter Specification Standard (LMSS) to documents☆13Aug 15, 2024Updated 2 years ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆545Feb 10, 2025Updated last year
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆750Aug 16, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆59Mar 26, 2024Updated 2 years ago
- ☆47Nov 25, 2024Updated last year
- Make triton easier☆49Sep 3, 2026Updated 2 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆539Aug 1, 2024Updated 2 years ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆195Jul 10, 2024Updated 2 years ago
- Utilities for PyTorch distributed☆26Feb 27, 2025Updated last year
- LLM KV cache compression made easy☆1,245Updated this week
- Claudette's sister, a helper for OpenAI GPT☆45May 20, 2026Updated 5 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆162Dec 4, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Evaluate state-of-the-art sparse embedding models on the LIMIT dataset (`limit-small` and `limit`) from google's paper `On the Theoretica…☆16Sep 4, 2025Updated last year
- Load any clip model with a standardized interface☆23Oct 20, 2025Updated last year
- A sample pattern for running CI tests on Modal☆21Apr 12, 2025Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆186Jul 12, 2024Updated 2 years ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆102Sep 4, 2024Updated 2 years ago
- Triton-based implementation of Sparse Mixture of Experts.☆281Oct 3, 2025Updated last year
- Easy control for Key-Value Constrained Generative LLM Inference(https://arxiv.org/abs/2402.06262)☆62Feb 13, 2024Updated 2 years ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆438Nov 20, 2025Updated 11 months ago
- ☆18Apr 3, 2023Updated 3 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆173Feb 15, 2025Updated last year
- msglm makes it a little easier to create messages for language models like Claude and OpenAI GPTs.☆15Apr 6, 2026Updated 7 months ago
- [ICLR2025] Code and data for paper: Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasonin…☆46Mar 10, 2025Updated last year
- Unified KV Cache Compression Methods for Auto-Regressive Models☆1,394Aug 13, 2026Updated 2 months ago
- Deployment examples for FastHTML☆43Sep 11, 2024Updated 2 years ago
- 16-fold memory access reduction with nearly no loss☆107Mar 26, 2025Updated last year
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆393Sep 25, 2024Updated 2 years ago