fix: fix endpoint-type in multimodel script

Signed-off-by: lkomali <[email protected]>

Author: lkomali

examples/serve/aiperf_client.sh

@@ -0,0 +1,16 @@
+#! /usr/bin/env bash
+
+aiperf profile \
+    -m TinyLlama-1.1B-Chat-v1.0 \
+    --tokenizer TinyLlama/TinyLlama-1.1B-Chat-v1.0 \
+    --endpoint-type chat \
+    --random-seed 123 \
+    --synthetic-input-tokens-mean 128 \
+    --synthetic-input-tokens-stddev 0 \
+    --output-tokens-mean 128 \
+    --output-tokens-stddev 0 \
+    --request-count 100 \
+    --request-rate 10 \
+    --profile-export-file my_profile_export.json \
+    --url localhost:8000 \
+    --streaming

examples/serve/aiperf_client_for_multimodal.sh

@@ -0,0 +1,19 @@
+#! /usr/bin/env bash
+
+aiperf profile \
+    -m Qwen2.5-VL-3B-Instruct \
+    --tokenizer Qwen/Qwen2.5-VL-3B-Instruct \
+    --endpoint-type chat \
+    --random-seed 123 \
+    --image-width-mean 64 \
+    --image-height-mean 64 \
+    --image-format png \
+    --synthetic-input-tokens-mean 128 \
+    --synthetic-input-tokens-stddev 0 \
+    --output-tokens-mean 128 \
+    --output-tokens-stddev 0 \
+    --request-count 5 \
+    --request-rate 1 \
+    --profile-export-file my_profile_export.json \
+    --url localhost:8000 \
+    --streaming