[Question] Request for detailed hardware specs and quantization details

Hi team, great work on InferenceX. I couldn't find detailed hardware configurations in the docs and need clarification on a few critical points to interpret the benchmarks correctly: 1. GPU Details: - Confirmed form factor: Are the H200 SXM5 or PCIe? (Docs mention "sxm" but lack specifics). - VRAM: Is it the standard 141GB per GPU? - Host: What are the CPU models and System RAM sizes used? 2. Networking: - For multi-node tests, what is the interconnect? Specifically, are you using ConnectX-7 NICs and what is the bandwidth (400G/800G)? 3. Model Quantization (GLM-4/5.1): - Native precision for GLM models is typically BF16. The results only show FP4/FP8. - Are these benchmarks running quantized versions of the models? - Were any BF16 (native) baselines tested for comparison? 5. DeepSeek-V4 Pro Memory Fit: - DeepSeek-V4 Pro (even with aggressive FP8) reportedly requires ~1.6TB of VRAM. - How does this fit on an 8x H200 (141GB) node (Total ~1.1TB)? - Is there heavy offloading to CPU/RAM involved, or is a specific sparse/MoE loading strategy used that reduces the active memory footprint significantly below 1.6TB? A quick update to the README with a hardware spec table and quantization details would be very helpful. Thanks! <img width="2400" height="668" alt="Image" src="https://github.com/user-attachments/assets/e0915e3c-7667-4fba-afee-351d13709982" />