Revision as of 04:11, 21 September 2026

Topics

🤖 Agent	🧠 Model	🚀 Engine	⚙️ GPU & Driver	Evaluation
ZooCode axe MCP	hf (Model Management) Qwen 3.8 27B Gemma 4 Devstral Small 2 24B Muse Glimmer Experience	llama-swap bifrost vLLM ComfyUI llama.cpp for SYCL llama.cpp for CUDA OVMS llama.cpp for OpenVINO llama.cpp for TurboQuant lemonade for AMD NPU SGLang	Intel Arc Pro B70 Install driver Install oneAPI (SYCL) Install OpenVINO .bashrc for B70 Experiment NVIDIA RTX 3060 Install driver AMD Ryzen AI 7 350 Experiment Tools Install nvtop lact PCIe Trouble Shooting	Performance Security Hallucination

@@ Line 52: / Line 52: @@
 * [https://huggingface.co/datasets/ScaleAI/SWE-bench_Pro?leaderboard_max_params=32B SWE Pro Benchmark for models < 32B]
 * [https://storage.openvinotoolkit.org/repositories/openvino/packages/2026.3/linux/ OpenVINO 2026.3 supports Ubuntu 26] - 2026-08-04
+= Test =
+<quickmmd name="models-handling-infra">
+flowchart LR
+  A(LiteLLM)
+  B(llama-swap)
+  C1(llama.cpp)
+  C1(vLLM)
+</quickmmd>
 = Decision Tree for tinkering with Intel Arc Pro B70 =