docs: add verified vLLM Docker image to Deploy section (#2)

Update config.json and hf_quant_config.json

Add GPQA Diamond scores to evaluation table (baseline 0.894, NVFP4 0.891)

Fix benchmark note: remove inaccurate FP8 baseline line, correct max tokens to 384000

Remove Artificial Analysis (AA) reference numbers from evaluation table

Update model card: add Flash evaluation results and vLLM/SGLang deployment sections

Keep MTP block in source precision

Add files using upload-large-folder tool

Add files using upload-large-folder tool

initial commit