Skip to content
#

intel-arc-b70

Star

Here are 5 public repositories matching this topic...

Language: All
Filter by language
All 5 Python 2 Shell 2 C 1

SergiioB / intel-arc-pro-b70-inference-cookbook

Star 178

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!!

moe mtp sycl intel-gpu intel-arc llama-cpp vllm llm-inference local-ai speculative-decoding battlemage intel-arc-b70
  • Updated Oct 15, 2026
  • Python

chriswagner-ai / intel-arc-b70-vllm-multi-gpu

Star 7

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).

linux gpu triton quantization multi-gpu xe2 oneapi level-zero cachyos intel-xpu fp8 intel-arc vllm llm-inference bmg-g31 battlemage xe-driver tensor-parallel intel-arc-pro intel-arc-b70
  • Updated Jun 13, 2026
  • Shell

epsilonagentx / intel_arc_gpu_llm

Star 2

Docker Compose stack for serving a local, OpenAI-compatible LLM (vLLM on Intel XPU) on an Intel Arc Pro B60 GPU — reproducible config with operator and developer docs.

docker-compose self-hosted inference-server intel-gpu oneapi xpu llm-serving vllm local-llm llm-inference gpt-oss gpt-oss-20b gemma4-26b-a4b intel-arc-b70 intel-arc-b60 arc-gpu intel-arc-pro-b70 intel-arc-pro-b60 intel-arc-gpu-llm
  • Updated Oct 7, 2026
  • Shell

Add this topic to your repo

To associate your repository with the intel-arc-b70 topic, visit your repo's landing page and select "manage topics."

Learn more