level-zero

A pure C inference engine designed for Intel Xe-LP iGPUs and Gemma 4 26B-A4B QAT.

Model Dispatch and Memory Allocator: an LLM inference engine for the hardware you own. Custom CPU, ROCm, Vulkan, CUDA, Metal and Level Zero kernels, exact memory admission, mTLS gRPC and private federation.

Intel LevelZero JNI library for TornadoVM

Pure-Go GPU/NPU compute wrapper for Intel NEO driver Level Zero APIs.

Native inference for Intel Arc GPUs (SYCL / Level Zero, XMX): Qwen3.8-Flash-Next, GLM-5.3-Flash and DeepSeek-V4.1-Flash. Alpha. A fork of XeStrata, targeting Project Maya's models.

Field-tested guide: multi-GPU vLLM tensor-parallel (TP=2/TP=4) on Intel Arc Pro B70 (Battlemage BMG-G31, Xe2) on Linux. Driver setup (xe force_probe=e223), bare-metal vLLM + oneAPI 2025.3, the compute-runtime multi-root USM + triton-xpu init_devices fixes, FP8/int4-AutoRound quant, root-cause error reports. AI-agent readable (AGENTS.md).

Unofficial community hub for Intel Arc Pro B70/B-series, Intel XPU, oneAPI, OpenVINO, PyTorch XPU, vLLM, llama.cpp, setup guides, benchmarks, and patches.

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

Latest Ollama, accelerated on Intel Arc & Xe iGPUs via SYCL/oneAPI – auto-rebuilt for every upstream release. Docker + Open WebUI ready.

Native, zero-bloat local LLM runner and server purpose-built for Intel Arc GPUs & AI Boost NPUs with dual-silicon speculative decoding and drop-in Ollama/OpenAI API parity.

Pure-Rust reimplementation of VkFFT with typed planning, kernel IR, and multi-backend GPU runtimes

A simple utility to count the number of compute and copy engines on Intel GPUs.

Run LLMs on Intel GPUs at full speed — Ollama with SYCL backend, 2x faster than Vulkan (Arc A770, Core Ultra, Flex/Max)

PoC for the acceleration of the core Math functions in Llama2.c to run on GPUs with Shared Memory

Benchmarks, validators and GPU driver bug reproducers for the goldbach-l0 Goldbach verifier

Run Microsoft TRELLIS.2 image-to-3D on Intel Arc GPUs (Arc Pro B60, 24 GB) with PyTorch XPU in Docker. No CUDA or NVIDIA needed.

vLLM running natively on Windows on two Intel Arc Pro B60s - two cards faster than one. Port notes, probes, build scripts and measurements.

Xe2 dual-B70 kernel and 2x2 parallelism lab (TP=2, PP=2)

Pioneer documentation: OpenFOAM CFD GPU offloading on Intel Arc Pro B70 Pro (Battlemage Xe2). Hardware excellent (FP64 96%, kernel latency CUDA-par), software stack not ready (GPU 66% idle, no working strong preconditioner in Ginkgo 1.10 SYCL). 14 bugs documented + direct VRAM/profiling data.

Configurable Windows performance HUD with DX11, DX12 and Vulkan test harness