[Diffusion] Enable request-level batching for Boogu-Image (TI2I) (#7227)

Signed-off-by: Shenglei Fu <sfu@confluent.io>
Signed-off-by: Shenglei Fu <117230642+ShengleiFu@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>

benchmarks/diffusion/backends.py

@@ -107,6 +107,8 @@ async def async_request_image_edits(
 
     if extra_body.get("guidance_scale") is not None:
         form.add_field("guidance_scale", str(extra_body["guidance_scale"]))
+    if extra_body.get("guidance_scale_2") is not None:
+        form.add_field("guidance_scale_2", str(extra_body["guidance_scale_2"]))
     if extra_body.get("negative_prompt") is not None:
         form.add_field("negative_prompt", str(extra_body["negative_prompt"]))
     if extra_body.get("true_cfg_scale") is not None:

benchmarks/diffusion/diffusion_benchmark_serving.py

@@ -1107,6 +1107,11 @@ def calculate_metrics(
     error_outputs = [o for o in outputs if not o.success]
 
     num_success = len(success_outputs)
+    error_log_path = os.environ.get("BENCH_ERROR_LOG")
+    if error_outputs and error_log_path:
+        with open(error_log_path, "a") as f:
+            for output in error_outputs:
+                f.write(f"ERROR latency={output.latency:.3f} detail={output.error!r}\n")
     latencies = [o.latency for o in success_outputs]
     peak_memories = [o.peak_memory_mb for o in success_outputs if o.peak_memory_mb > 0]