Here are
4 public repositories
matching this topic...
Community-maintained llama.cpp SYCL Docker optimized for Intel Arc Pro B70 (Battlemage). Latest oneAPI/compute-runtime/IGC, B70-specific AOT build, all features enabled (Flash Attention, MTP, reorder kernels, no GGML_SYCL_DISABLE_OPT).
b70ctl — TUI that installs and serves qualified LLM model packs on Intel Arc Pro B70 GPUs (vLLM/XPU): Qwen3.8 27B, Qwen3.6 35B A3B, Qwen3.8 Flash Next, MTP, DFlash2
Not another fork. Superb LLM inference server for Intel Arc Pro B70 | 50+% vLLM 🔥| 5x llama.cpp 💩
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.
Add this topic to your repo
To associate your repository with the
b70
topic, visit your repo's landing page and select "manage topics."
Learn more
You can’t perform that action at this time.