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.
☆149Aug 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☆43Aug 14, 2024Updated last year
- ☆21Apr 17, 2025Updated 11 months ago
- ☆14Jun 4, 2024Updated last year
- ☆306Jul 10, 2025Updated 8 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆376Jul 10, 2025Updated 8 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆155Feb 20, 2025Updated last year
- KV cache compression for high-throughput LLM inference☆153Feb 5, 2025Updated last year
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆668Feb 24, 2026Updated 3 weeks ago
- ☆47Nov 25, 2024Updated last year
- Make triton easier☆50Jun 12, 2024Updated last year
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆57Mar 26, 2024Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆144Dec 4, 2024Updated last year
- The Official Implementation of Ada-KV [NeurIPS 2025]☆128Nov 26, 2025Updated 3 months ago
- LLM KV cache compression made easy☆971Mar 13, 2026Updated last week
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,196Mar 9, 2026Updated last week
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆54Mar 27, 2024Updated last year
- ☆36Mar 17, 2025Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆94Sep 4, 2024Updated last year
- A simple python wrapper for using the Caddy API☆27Mar 4, 2026Updated 2 weeks ago
- msglm makes it a little easier to create messages for language models like Claude and OpenAI GPTs.☆14Jan 29, 2026Updated last month
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆180Jul 12, 2024Updated last year
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆531Feb 10, 2025Updated last year
- ☆162Feb 15, 2025Updated last year
- Easy control for Key-Value Constrained Generative LLM Inference(https://arxiv.org/abs/2402.06262)☆62Feb 13, 2024Updated 2 years ago
- ☆18Apr 3, 2023Updated 2 years ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆506Aug 1, 2024Updated last year
- [ICLR2025] Code and data for paper: Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasonin…☆40Mar 10, 2025Updated last year
- Fast, Modern, and Low Precision PyTorch Optimizers☆128Dec 29, 2025Updated 2 months ago
- Vortex: A Flexible and Efficient Sparse Attention Framework☆49Jan 21, 2026Updated last month
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- A sample pattern for running CI tests on Modal☆19Apr 12, 2025Updated 11 months ago
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆57Nov 20, 2024Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆359Nov 20, 2025Updated 4 months ago
- ☆235Jun 11, 2024Updated last year
- ☆20Jul 12, 2023Updated 2 years ago
- Triton-based implementation of Sparse Mixture of Experts.☆270Oct 3, 2025Updated 5 months ago
- ☆52May 13, 2024Updated last year
- Transform is the main building block of data pipelines in fastai. And elsewhere if you want.☆32Jan 29, 2026Updated last month
- Run python scripts, auto-installing their dependencies in cached, isolated environments☆32Oct 8, 2024Updated last year