Models Take Notes at Prefill: KV Cache Can Be Editable and Composable (arXiv:2606.17107) — paper, code, results, and interactive companion.
☆16Nov 9, 2026Updated this week
Alternatives and similar repositories for programmable-kv
Users that are interested in programmable-kv are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Executable memory for personalized agents: represent a user's memory as typed Python state + constraints an interpreter can run, instead …☆19Jul 29, 2026Updated 3 months ago
- A user's facts become a few rows in a content-addressed memory table — not a rewrite of the model. Paper, code, data, and interactive sit…☆18Updated this week
- ☆24Updated this week
- ☆17Feb 22, 2026Updated 8 months ago
- ☆12Jun 2, 2026Updated 5 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A high-performance, RDMA-native data-plane library for large-scale heterogeneous memory pools, developed by the Tencent Astral Network Te…☆35Aug 6, 2026Updated 3 months ago
- Block-GTQ: RoPE-aware bit allocation for KV-cache quantization☆17Oct 29, 2026Updated 2 weeks ago
- ☆28Jan 22, 2026Updated 9 months ago
- Official implementation of "SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching" (COLM 2025). A novel KV cache com…☆15Sep 29, 2025Updated last year
- [MLSys 2026] Official code of SkipKV: Selectively Skip KV Generation and Storage for Efficient Inference with Large Reasoning Models.☆16Oct 26, 2026Updated 2 weeks ago
- AI-based command line tool to quickly generate standardized commit messages.☆10Apr 25, 2026Updated 6 months ago
- Clean-room reimplementation of ClickNP (SIGCOMM 2016) on Alveo U50☆29May 28, 2026Updated 5 months ago
- A terminal-based AI coding assistant built in Rust.☆28May 23, 2026Updated 5 months ago
- Understanding AI-DLC: A Living Open-Source Book Powered by a GitHub-Native Writing System. 《深入理解 AI-DLC》：持续更新的开源…☆39Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆50Oct 16, 2025Updated last year
- ☆14Jun 3, 2026Updated 5 months ago
- ☆12Updated this week
- Official implementation of STaR-KV: training-free spatio-temporal KV cache compression for efficient GUI vision-language models.☆22Oct 17, 2026Updated 3 weeks ago
- Hypercube's blog☆11Jan 6, 2019Updated 7 years ago
- Efficient GPU communication over multiple NICs.☆31Nov 20, 2025Updated 11 months ago
- A benchmark for UDF queries☆14Updated this week
- ☆11Aug 14, 2025Updated last year
- ☆13Apr 9, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Upstream-compatible vLLM fork for domestic hardware enablement and AGI4S serving☆12Aug 31, 2026Updated 2 months ago
- A distributed stream querying engine that provides sub-millisecond stateful query at millions of queries per-second over fast-evolving li…☆10Jul 18, 2018Updated 8 years ago
- Desktop Git diff reviewer with inline commenting for AI coding agent workflows☆33Mar 24, 2026Updated 7 months ago
- ☆14Jun 18, 2026Updated 4 months ago
- 在原版multiple-attention,重新修订数据处理方式和训练代码☆10Mar 21, 2024Updated 2 years ago
- Incremental View Maintenance support for DuckDB☆18Oct 24, 2023Updated 3 years ago
- Voice input that transcribes what you said, grounded in what's on your screen. macOS, Windows, Android, iOS.☆55Nov 1, 2026Updated last week
- A multistate dataset for colposcopy image classification of cervical cancer screening☆11Dec 4, 2020Updated 5 years ago
- ☆12Jul 19, 2022Updated 4 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- PreAct: Computer-Using Agents that Get Faster on Repeated Tasks (arXiv:2606.17929). Compile successful runs into verified state-machine p…☆19Jun 17, 2026Updated 4 months ago
- code for infocom 2021 paper MANDA☆11May 30, 2023Updated 3 years ago
- ☆19Aug 16, 2025Updated last year
- DEPRECATED REPOSITORY. ROCm Inference Transfer Library (RIXL) is a port of the NIXL library for AMD GPUs. See README_rocm.md for AMD spe…☆15Updated this week
- ☆18Updated this week
- A benchmark framework for decision forest inferences☆11Jan 19, 2024Updated 2 years ago
- The official repo for the paper "Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching"☆17Mar 17, 2025Updated last year
Are these results useful?