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
Alternatives and similar repositories for FastGen
Users that are interested in FastGen are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆153Aug 9, 2024Updated 2 years ago
- ☆16Jun 4, 2024Updated 2 years ago
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆59Mar 26, 2024Updated 2 years ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆51Jun 19, 2024Updated 2 years ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆414Jul 10, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆541Aug 1, 2024Updated 2 years ago
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆19Oct 21, 2024Updated 2 years ago
- Official implementation of the paper: "A deeper look at depth pruning of LLMs"☆15Jul 24, 2024Updated 2 years ago
- [NeurIPS 2024] Implementation of paper - D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models☆26Apr 9, 2025Updated last year
- [ICLR 2024] Jaiswal, A., Gan, Z., Du, X., Zhang, B., Wang, Z., & Yang, Y. Compressing llms: The truth is rarely pure and never simple.☆27Apr 21, 2025Updated last year
- A high-throughput LLM serving engine with non-uniform KV cache compression, built on vLLM☆16Nov 9, 2026Updated last week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆162Dec 4, 2024Updated last year
- ☆11May 24, 2024Updated 2 years ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆143Nov 26, 2025Updated 11 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆440Aug 13, 2024Updated 2 years ago
- This repository contains the code for the paper: SirLLM: Streaming Infinite Retentive LLM☆60May 28, 2024Updated 2 years ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆441Nov 20, 2025Updated 11 months ago
- [ACL Findings 2026] Official Implementation of "FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acc…☆34Apr 14, 2026Updated 7 months ago
- ☆86Jun 2, 2026Updated 5 months ago
- [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification☆32Mar 30, 2025Updated last year
- ICLR 2025: Needle Threading☆11May 24, 2025Updated last year
- ☆11Jun 9, 2025Updated last year
- To mitigate position bias in LLMs, especially in long-context scenarios, we scale only one dimension of LLMs, reducing position bias and …☆13Jun 18, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆14Oct 3, 2024Updated 2 years ago
- Kinetics: Rethinking Test-Time Scaling Laws☆87Jul 11, 2025Updated last year
- ☆37Oct 10, 2024Updated 2 years ago
- Pytorch implementation for "Compressed Context Memory For Online Language Model Interaction" (ICLR'24)☆64Apr 18, 2024Updated 2 years ago
- WIPE implementation☆12Nov 26, 2023Updated 2 years ago
- ☆29Dec 2, 2024Updated last year
- ☆15Apr 11, 2024Updated 2 years ago
- ☆24Mar 7, 2025Updated last year
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,231Updated this week
- 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.
- (ACL2025 oral) SCOPE: Optimizing KV Cache Compression in Long-context Generation☆37May 28, 2025Updated last year
- Codebase for ICML'24 paper: Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs☆28Jun 25, 2024Updated 2 years ago
- ACL 2023☆38Jun 6, 2023Updated 3 years ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆545Feb 10, 2025Updated last year
- 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
- Explore Inter-layer Expert Affinity in MoE Model Inference☆17May 6, 2024Updated 2 years ago
- Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals☆15Oct 21, 2026Updated 3 weeks ago
Are these results useful?