llama.cpp OpenAI-compatible server on Vulkan for AMD Strix Halo (gfx1151), GGUF weights pinned to GTT not VRAM. Serves poolside Laguna S 2.1, Gemma 4 and Qwen3.6 GGUFs on the stock Vulkan image, plus an opt-in ROCmFP4 + MTP stack (Ubuntu 26.04 + TheRock ROCm 7.13). Docker Compose, with real measured benchmarks.

Serve Poolside Laguna S 2.1 (NVFP4) on the NVIDIA DGX Spark (GB10) without hanging your box. Working stack, crash-safe configs, benchmarks, and the exact gotchas.

GPIO'4'Cars, the way to drive your car with N2!

Poolside Laguna S 2.1: Run 1M Context Locally (Tested) - Complete overview, benchmarks, local setup guides (vLLM, SGLang, llama.cpp), and test suite for Laguna S 2.1 118B MoE.

poolside Laguna-S-2.1 INT4 + DFlash speculative decoding on 4x RTX 3090: 200K context, 282 tok/s peak decode, gate-proven with a 190K-token prompt. Full levers menu + failure catalog.

Multi-currency browser extension wallet supporting Laguna Chain

OpenCode plugin for the Poolside AI model provider with live model discovery

Bounded, read-only Agy, Hermes, and OpenCode second opinions for Codex, with OpenCode Zen free models and a short /opencode command.

generic_system_google-user 16 BP4A.251205.006 14401865 release-keys

generic_system_google-user 16 BP4A.251205.006.E1 14586962 release-keys

generic_system_google-user 16 BP4A.251205.006 14401865 release-keys

Reverse engineering du NavCore 9.884 embarqué Renault (codename beaumont)

Локальный LLM-провайдер для проекта slovo — Ollama c Laguna XS.2 (33B/3B MoE) в Docker с проброшенной NVIDIA GPU. Оптимизирован под single-user агентские сессии на RTX 4070 Ti SUPER + i9-11900K.