Do multiple agents sharing a single asymmetrically-compressed KV pool produce quality output comparable to full-precision per-agent KV caches?
☆12Apr 26, 2026Updated 6 months ago
Alternatives and similar repositories for PolyKV
Users that are interested in PolyKV are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Concurrency Patch to enable on DSpark - DeepSeek V4 Flash/Pro C=16 can be modified for more☆12Jun 29, 2026Updated 4 months ago
- ☆30May 30, 2026Updated 4 months ago
- [EuroSys27] TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications☆14Oct 14, 2026Updated 2 weeks ago
- ☆18Jan 5, 2026Updated 9 months ago
- Sample code to demonstrate how to implement a simple chat that works on .NET MAUI, Blazor and Blazor Hybrid with SignalR☆10Feb 14, 2023Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- a mixed-precision gemm with quantize and reorder kernel.☆15Jul 22, 2025Updated last year
- Anta is Antithesis design system☆18Updated this week
- A cache-coherent vector execution fabric — sits in front of any vector store/lakehouse and makes queries fast. Part of the RuVector ecosy…☆15Oct 2, 2026Updated 3 weeks ago
- Realtime object detection on Android with Xamarin.Android and TensorFlow Lite (SSD MobileNet).☆11Sep 15, 2026Updated last month
- CloudlessOS☆14Aug 20, 2026Updated 2 months ago
- ruOS — an agentic desktop (a desktop that runs itself): computer-use MCP server + ruvnet-stack skills.☆19Aug 31, 2026Updated last month
- 🤖 🧰 Agent Skills — Create, manage, and execute reusable code-based tool compositions for AI agents.☆17Oct 18, 2026Updated last week
- A user-friendly editor tool has been developed to create or edit JSON configuration files:☆12Sep 9, 2025Updated last year
- NVFP4 KV cache for vLLM on SM120 (RTX PRO 6000) via FlashInfer FA2 explicit-SF-stride patch — ~1.5x fp8 pool at ~95-104% speed☆20Jun 5, 2026Updated 4 months ago
- 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.
- Prompt Engineering'i öğrenebileceğiniz Erdoğan Eker ile birlikte oluşturduğumuz bir kitap.☆12Sep 9, 2024Updated 2 years ago
- Local Laya System-1 judge MCP server + skill for oh-my-pi: typed decisions in milliseconds, zero LLM tokens☆10Sep 26, 2026Updated last month
- DGX Spark / GB10 vLLM Docker stack for large-model serving, presets, patches, and validation notes.☆12Jun 29, 2026Updated 4 months ago
- Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP / LangChain.☆17Oct 8, 2026Updated 3 weeks ago
- A MoE expert separation workbench for building, testing, and routing smaller specialist models with MetaHarness, Ruflo, and LatentMesh st…☆14Sep 5, 2026Updated last month
- keys- 1M context: Inkling-Small-NVFP4 + DSpark + NVFP4 KV on SGLang, sm_121a-optimized on Two DGX Sparks — one-shot agent-executable rec…☆10Aug 17, 2026Updated 2 months ago
- PlayList Animation using MAUI.☆14Nov 1, 2022Updated 3 years ago
- A community-owned map of LLM inference engine configurations — benchmarks, evals and coverage gaps, hosted on GitHub Pages. The repo is t…☆16Oct 19, 2026Updated last week
- Rust project generator with 7 typed templates — CLI, API server, WASM, game engine, embedded, library, workspace. cargo install cargo-for…☆16Oct 15, 2026Updated 2 weeks ago
- 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.
- ☆19Feb 18, 2025Updated last year
- agent multiplexer that lives in your terminal.☆14Updated this week
- Agent-ready two-node DGX Spark recipe for DeepSeek V4 Flash plus an optional Qwen Vision sidecar, with generic OpenAI-compatible, Hermes,…☆24Aug 10, 2026Updated 2 months ago
- ☆16Sep 25, 2026Updated last month
- Full GLM-5.3 (753B) served by TensorFold with tensor parallel 4 across four NVIDIA DGX Sparks: results, recipe, node settings, benches☆20Oct 13, 2026Updated 2 weeks ago
- An end-to-end framework for Agentic Reinforcement Learning.☆15Updated this week
- Honeycomb Lab — hex map + OpenAI gateway control plane for a home AI fleet☆17Updated this week
- ruvnet-only control plane for running an AI-agent company end-to-end — org-chart, budget-gated heartbeats, approval gates, signed audit t…☆20Updated this week
- Headless / multi-user serving-mode for the DGX Spark: free unified memory for vLLM by paring back the desktop. Companion to qwen3.5-122B-…☆20Jun 29, 2026Updated 4 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [ACL 2026 Main] Code for the paper "ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs"☆34Sep 21, 2026Updated last month
- Give the DeepSeek Harness (dsh) eyes with any text model + any vision model: a vision proxy for chat image attachments and an analyze_ima…☆12Sep 28, 2026Updated last month
- ☆16Updated this week
- EXLR8: a DGX Spark tuned quantization format☆14Updated this week
- Consistent dev environments anywhere. Define once in YAML, deploy to Docker, Fly.io, or DevPod. Pre-built extensions for AI, languages & …☆16Updated this week
- GLM-5.2 QuantTrio TP=4+DCP2 on 4x NVIDIA DGX Spark (GB10) — tuned and measured under a real agent workload. Adaptive MTP, the indexer law…☆19Aug 24, 2026Updated 2 months ago
- Working recipe: MiniMax-M3 NVFP4 at tensor-parallel 3 across 3x DGX Spark (GB10/sm_121) with clean tool-calling. Includes the head-node O…☆16Jul 13, 2026Updated 3 months ago