oneapi

支持 AnyRouter、AgentRouter 的多平台多账号签到，理论兼容所有基于 NewAPI、OneAPI 的平台。

Extension for Scikit-learn is a seamless way to speed up your Scikit-learn application

Archived oneAPI specification sources. The current dynamic specification is maintained on the UXL Foundation website and in project documentation.

Tools to run and parse MKL verbose mode

An actively maintained fork of ConanCenter with an emphasis on CV, ML and robotics capabilities on edge devices

A fork of ConanCenter with an emphasis on CUDA, CV, ML and robotics capabilities on edge devices

Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible API.

Treatise of Medical Image Processing (TMIP) v0.2.0

一款针对 LLM 输入侧审查的精确逆向分析工具。自动定位 NewAPI、OneAPI 及任何实施基于字典规则进行 Prompt 过滤的 API 网关中的敏感关键词 | A precision reverse-engineering tool for LLM input censorship. Automatically pinpoints blocked keywords in NewAPI, OneAPI, and any API gateways enforcing dictionary-based prompt filtering.

VMAFx: perceptual video quality assessment (VMAF), GPU-accelerated and SIMD-tuned. CUDA, SYCL, HIP and Metal backends checked against the CPU scores, AVX2/AVX-512/NEON, tiny-AI models, an MCP server, Kubernetes/Helm deployment. Fork of Netflix/vmaf; fork code EUPL-1.2, Netflix code BSD-2-Clause-Patent.

AstrBot 多模型生图：七个渠道一个指令，支持图生图与 ComfyUI 多工作流

Per-precision XMX (matrix engine) profiling for Intel Arc GPUs via Level Zero metric streamers — observes any workload without wrapping it

🕵️♂️ Analyze and reverse engineer keyword filtering in large language models to enhance compliance and operational insights.

Sample data parallel extensions built with oneAPI DPC++

Reproducible Intel XPU deployment and validation for vLLM serving Qwen3.6 35B-A3B W4G32 with MTP2.

支持 AnyRouter、AgentRouter 的多平台多账号签到，理论兼容所有基于 NewAPI、OneAPI 的平台。

It's a Face recognition project which mark Attendance in real time. Built using Python libraries

GUI manager for llama.cpp (SYCL) with OpenAI-compatible API and automatic model switching.

Create, update, import, export, and delete Zscaler ZIA DLP policies via OneAPI

Static reverse engineering of the AMD DLSS NR module (dlssnr_amd_pass1.dll) - kernel parameter spec, weight container format, and an Intel XMX porting feasibility assessment targeting Xe-HPG/Xe2 and later. Three open gaps; help wanted.