oneAPI Specification source files
-
Updated
Jul 21, 2026 - Python
oneAPI Specification source files
Open recipes, engine patches, and benchmark harnesses for LLM inference on Intel Arc Pro B60/B70 (Battlemage, Xe2). MoE 35B at 160 t/s decode / 7.5K t/s prefill single-stream, 27B at 50~ t/s decode / 1.7K t/s prefill single stream. vLLM XPU MTP unlocked. Muse Glimmer recipe added!!
Makes Intel Arc Pro B70 GPUs actually fast on Ubuntu Server. 11 llama.cpp cherry-picks that fix the big B70 bugs (MoE slot-init SEGV, Q8_0 reorder crash, OOM reorder, missing BF16 GET_ROWS, wrong Xe2 warptile, slow K-quant DMMV, etc.) + Mesa 26 + runtime env workarounds + SYCL/Vulkan backend-selection rules. 2-7x speedup on 4x B70, bench-verified.
VMAFX — perceptual video quality assessment. Modernized fork-evolved with SYCL/CUDA/HIP/Metal backends, tiny-AI models, MCP server, cloud-native (k8s/Helm) deployment. BSD-2-Clause-Patent.
Plug-and-play llama.cpp runtime for Intel Arc GPUs. Auto-detects your card, picks safe SYCL defaults, and exposes an OpenAI-compatible API.
ComfyUI custom node for llama-cpp-python with Intel GPU SYCL acceleration. Adapted for 0.3.39+ MTMD rewrite. Pair with allanmeng/llama-cpp-python-sycl-windows for SYCL whl builds.
Automated CUDA-to-ROCm GPU kernel translation via semantic BridgeIR. 316 HIP API mappings, wavefront-aware optimization, MFMA targeting, 6 multi-target backends. Break free from CUDA vendor lock-in.
GUI manager for llama.cpp (SYCL) with OpenAI-compatible API and automatic model switching.
DORSAL scripts
Boltz-2 on Intel Arc — NVIDIA-free protein folding + binding affinity (AlphaFold3-class) via torch.xpu.
Hardware monitoring, benchmarks, and technical reports for NPUs (Intel Meteor Lake, Apple Silicon, Qualcomm).
Run a 30B-class LLM, vision, image generation and a local coding agent on an Intel ThinkPad (Arc 140T iGPU) — host-native, reproducible
Add a description, image, and links to the sycl topic page so that developers can more easily learn about it.
To associate your repository with the sycl topic, visit your repo's landing page and select "manage topics."