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.
☆148Aug 9, 2024Updated 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:
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆44Aug 14, 2024Updated last year
- ☆14Jun 4, 2024Updated last year
- ☆21Apr 17, 2025Updated 10 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆48Jun 19, 2024Updated last year
- ☆301Jul 10, 2025Updated 7 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆372Jul 10, 2025Updated 7 months ago
- A simple python wrapper for using the Caddy API☆27Feb 3, 2026Updated 3 weeks ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆155Feb 20, 2025Updated last year
- KV cache compression for high-throughput LLM inference☆154Feb 5, 2025Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆144Dec 4, 2024Updated last year
- Make triton easier☆50Jun 12, 2024Updated last year
- A chat implementation for FastHTML☆11Sep 14, 2025Updated 5 months ago
- msglm makes it a little easier to create messages for language models like Claude and OpenAI GPTs.☆14Jan 29, 2026Updated last month
- Boosting 4-bit inference kernels with 2:4 Sparsity☆93Sep 4, 2024Updated last year
- ☆18Apr 3, 2023Updated 2 years ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆659Sep 30, 2025Updated 5 months ago
- ☆21Mar 3, 2025Updated 11 months ago
- Evaluate state-of-the-art sparse embedding models on the LIMIT dataset (`limit-small` and `limit`) from google's paper `On the Theoretica…☆15Sep 4, 2025Updated 5 months ago
- LLM KV cache compression made easy☆936Updated this week
- The Official Implementation of Ada-KV [NeurIPS 2025]☆128Nov 26, 2025Updated 3 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,188Sep 30, 2025Updated 5 months ago
- A simple uv workspace☆19Apr 5, 2025Updated 10 months ago
- Fast, Modern, and Low Precision PyTorch Optimizers☆125Dec 29, 2025Updated 2 months ago
- ☆235Jun 11, 2024Updated last year
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆57Mar 26, 2024Updated last year
- A sample pattern for running CI tests on Modal☆19Apr 12, 2025Updated 10 months ago
- Source-to-Source Debuggable Derivatives in Pure Python☆15Jan 23, 2024Updated 2 years ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆177Jul 12, 2024Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆524Feb 10, 2025Updated last year
- ☆48Nov 25, 2024Updated last year
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- ☆159Feb 15, 2025Updated last year
- Using short models to classify long texts☆21Mar 8, 2023Updated 2 years ago
- Vortex: A Flexible and Efficient Sparse Attention Framework☆48Jan 21, 2026Updated last month
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆55Mar 27, 2024Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆266Oct 3, 2025Updated 4 months ago
- Utilities for Training Very Large Models☆58Sep 25, 2024Updated last year
- A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.☆382Jul 8, 2025Updated 7 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆174Jul 10, 2024Updated last year