Update device/nvidia-agx-thor/nvidia-diffusiongemma-26B-A4B-it-NVFP4.md

device/nvidia-agx-thor/nvidia-diffusiongemma-26B-A4B-it-NVFP4.md

@@ -1,4 +1,6 @@
-- 20260622
+- 20260622 only for vllm/vllm-openai:gemma container
+
+## serve
 
 ```bash
 sudo docker run --rm -it --name=vllm-diffusiongemma --gpus all --runtime=nvidia --ipc=host --network host  \
@@ -31,4 +33,31 @@ vllm/vllm-openai:gemma \
 	--override-generation-config '{"max_new_tokens": null}' \
 	--mm-processor-kwargs '{"max_soft_tokens": 1120}' \
 	--limit-mm-per-prompt '{"image": 7}'
+```
+
+## bench
+```bash
+vllm bench serve \
+  --model "/workspace/thor-wm/nvidia-diffusiongemma-26B-A4B-it-NVFP4" \
+  --served-model-name "nvidia/diffusiongemma-26B-A4B-it-NVFP4" \
+  --host localhost \
+  --port 8002 \
+  --dataset-name random \
+  --random-input-len 1024 \
+  --random-output-len 1024 \
+  --num-prompts 5 \
+  --max-concurrency 1
+```
+
+```bash
+vllm bench serve \
+  --model "/workspace/thor-wm/nvidia-diffusiongemma-26B-A4B-it-NVFP4" \
+  --served-model-name "nvidia/diffusiongemma-26B-A4B-it-NVFP4" \
+  --host localhost \
+  --port 8002 \
+  --dataset-name random \
+  --random-input-len 1024 \
+  --random-output-len 1024 \
+  --num-prompts 32 \
+  --max-concurrency 8
 ```