Revision as of 01:10, 1 October 2026

Topics

🤖 Agent	🧠 Model	🚀 Engine	⚙️ GPU & Driver	📊 Evaluation
ZooCode axe MCP	hf (Model Management) Qwen Image 2.1 Qwen 3.8 27B Gemma 4 Devstral Small 2 24B Experience	llama-swap vLLM ComfyUI llama.cpp for SYCL llama.cpp for CUDA llama.cpp for OpenVINO llama.cpp for TurboQuant 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 PCIe Trouble Shooting Comparison LM/GPU Comparison	Performance

@@ Line 54: / Line 54: @@
 flowchart LR
    A(LiteLLM)
-   B1(llama-swap)
+   B(vLLM<br>Qwen 3.8 27B)
-  B2(vLLM<br>Qwen 3.8 27B)
+   C1(Intel Arc Pro B70)
-   C(llama.cpp<br>Gemma 4 E4B)
+  C2(Intel Arc Pro B70)
-   A --> B1 & B2
+   A --> |Forward| B
-   B1 --> C
+  B --> |Tensor Parallelism| C1 & C2
+   C1 --- |XCCL| C2
 </quickmmd>