-
Università di Pavia
- Milano
- https://orcid.org/0000-0003-0105-3449
- @gevero
Starred repositories
Official code for the paper "Scaling Multilingual Visual Speech Recognition"
Headless 3D and VFX engine for agents. Research preview.
WebGL 3D plotting for Jupyter: meshes, isosurfaces, volumes, voxels and point clouds from NumPy arrays, with a path-traced cinematic renderer.
Blender add-on to design, simulate, align & render optical setups — live beam tracing, kinematic-mount auto-alignment, polarization (Jones/Stokes), interference fringes, Gaussian beams, wavelength …
DeepSeek Harness: Everything is a Plugin.
Pty-Chi is a Python library for ptychographic image reconstruction.
LLM Inference Engine for Metal, CUDA and Vulkan.
A Python package for barycentric rational and polynomial interpolation and approximation.
Reverse engineer anything with agents, from app behavior down to native binaries.
Browser-based 2D optical workbench: draw a setup, trace it live, read the simulated detectors, share it as a link or a paper-ready figure.
🏡 Open source home automation that puts local control and privacy first.
Qwen3.8-Flash-Next-NVFP4-vLLM-Dual-DGX-Spark
GLM-5.3-Flash (NVFP4) on 2x NVIDIA DGX Spark - vLLM TP2, 262K context, MTP. World-first deploy recipe: 7 day-0 bugs found and fixed, patched sm121 image, probes and full report.
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
DeepSeek-V4.1-Flash on two DGX Sparks: EXL3 routed experts, 262k context, 2M-token KV, vision, tools, MTP, bundled with Pi
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
GPU FDTD for photonics: browser CAD workbench, Python project API and Torch-differentiable simulations on CUDA
Free surface integral equation (SIE) method software for modeling light scattering in homogeneous, periodic, and layered environments.
Agent Executor (AX) is Google's open agentic orchestration runtime
Web search and content extraction extension for Pi coding agent
Live truecolor terminal dashboard for a locally running LLM: tok/s, TTFT, GPUs, context, MTP acceptance, layer and real expert routing (llama.cpp)
A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.
The CSG engine. Fast and exact mesh booleans, spatial queries, arrangements, and remeshing. C++ with Python and TypeScript bindings.
Browser-based geometry processing. AI-controllable via MCP. Powered by trueform.
radphen-lab / scuff-em
Forked from HomerReid/scuff-emA comprehensive and full-featured computational physics suite for boundary-element analysis of electromagnetic scattering, fluctuation-induced phenomena (Casimir forces and radiative heat transfer)…