[Frontend] Add omni benchmark support for image and video endpoints

docs/cli/bench/serve.md

@@ -436,6 +436,76 @@ This should be seen as an edge case, and if this behavior can be avoided by sett
 
 </details>
 
+### Image / video generation
+
+For `/v1/images/generations`, `/v1/images/edits`, and `/v1/videos`, set `--endpoint` to that path and omit `--backend`. The endpoint path is registered as the bench request adapter, so a separate named backend is not required.
+
+Example (`/v1/images/generations`):
+
+```bash
+vllm bench serve --omni \
+  --endpoint /v1/images/generations \
+  --dataset-name random \
+  --model ~/models/Qwen/Qwen-Image \
+  --tokenizer ~/models/Qwen/Qwen-Image/tokenizer \
+  --max-concurrency 1 \
+  --num-warmups 2 \
+  --num-prompts 10 \
+  --random-input-len 64 \
+  --random-output-len 1 \
+  --ignore-eos \
+  --percentile-metrics e2el \
+  --extra-body '{
+    "num_inference_steps": 20,
+    "seed": 42,
+    "true_cfg_scale": 4.0
+  }'
+```
+
+If successful, following output is like:
+
+```text
+============ Serving Benchmark Result ============
+Successful requests:                     3  
+Failed requests:                         0  
+Maximum request concurrency:             1  
+Benchmark duration (s):                  8.42  
+Request throughput (req/s):              0.36  
+Peak concurrent requests:                2.00  
+-------------------Peak Memory--------------------
+Mean PEAK_MEMORY_MB (MB):                58832.00  
+Median PEAK_MEMORY_MB (MB):              58832.00  
+P99 PEAK_MEMORY_MB (MB):                 58832.00  
+----------------End-to-end Latency----------------
+Mean E2EL (ms):                          2798.16  
+Median E2EL (ms):                        2799.83  
+P99 E2EL (ms):                           2800.03  
+================== Image Result ==================
+Total images generated:                  3  
+Image throughput (img/s):                0.36  
+Average pixels per image:                1048576.00
+Mean denoise step latency (ms):          136.59  
+---------------- Image Generation ----------------
+Mean IMAGE_GENERATION (ms):              2731.84  
+Median IMAGE_GENERATION (ms):            2732.02  
+P99 IMAGE_GENERATION (ms):               2734.65  
+==================================================
+```
+
+Use the same pattern with `--endpoint /v1/images/edits` or `--endpoint /v1/videos` (and model-specific `--extra-body` as needed). Pure image/video runs omit the Text Result section when there is no generated text.
+
+`/v1/images/edits` defaults to **non-streaming JSON** (`stream=false`) so single-stage edit models are not rejected by the server. For multi-stage pipelines that need SSE (AR TTFT / image chunks), pass `"stream": true` in `--extra-body`.
+
+`/v1/videos` is an async job API: the client creates a job, then polls until `completed`/`failed`. Measured **e2el** therefore includes client poll sleep and any overshoot after the job actually finishes. Tune polling via `--extra-body`:
+
+- `poll_interval_s` (default `2.0`): sleep between status polls
+- `poll_timeout_s` (default `21600`, i.e. 6 hours): give up waiting for the job
+
+**VIDEO_RTF** prefers server-reported generation time when available:
+
+- `video_rtf = video_generation_time_ms / 1000 / video_duration`, where `video_generation_time_ms` comes from response `stage_durations` (or `inference_time_s` as fallback)
+- If generation time is missing, falls back to `e2el / video_duration` (this fallback *does* include poll overhead)
+
 ### Multi-Stage Benchmark
 
 <details class="admonition abstract" markdown="1">

tests/benchmarks/metrics/test_metrics.py

@@ -457,5 +457,136 @@ def test_text_benchmark_still_reports_ttft(capsys):
     assert "Time to First Token" in out, "text benchmarks must keep TTFT"
 
 
+# ============================================================================
+# Suppress text metrics for pure image / video endpoints
+# ============================================================================
+
+
+def _make_image_output(prompt_len: int) -> MixRequestFuncOutput:
+    output = MixRequestFuncOutput()
+    output.success = True
+    output.prompt_len = prompt_len
+    output.output_tokens = 0
+    output.generated_text = ""
+    output.ttft = 0.0
+    output.text_latency = 0.0
+    output.latency = 2.5
+    output.start_time = 0.0
+    output.itl = []
+    output.image_count = 1
+    output.image_generation_time_ms = 2000.0
+    output.image_pixels = 1024 * 1024
+    output.input_audio_duration = 0.0
+    output.error = ""
+    return output
+
+
+def _make_video_output(prompt_len: int) -> MixRequestFuncOutput:
+    output = MixRequestFuncOutput()
+    output.success = True
+    output.prompt_len = prompt_len
+    output.output_tokens = 0
+    output.generated_text = ""
+    output.ttft = 0.0
+    output.text_latency = 0.0
+    output.latency = 5.0
+    output.start_time = 0.0
+    output.itl = []
+    output.video_duration = 2.0
+    output.video_frames = 48
+    output.video_generation_time_ms = 4000.0
+    output.video_rtf = 2.0
+    output.input_audio_duration = 0.0
+    output.error = ""
+    return output
+
+
+_MEDIA_PERCENTILE_METRICS = ["e2el", "ttft"]
+
+
+def test_pure_image_benchmark_omits_text_result(capsys):
+    """Pure image generation must not print Text Result or invent peak tok/s."""
+    outputs = [_make_image_output(64), _make_image_output(64)]
+
+    metrics, actual_output_lens = calculate_metrics(
+        input_requests=[],
+        outputs=outputs,
+        dur_s=5.0,
+        tokenizer=None,
+        selected_percentiles=[99.0],
+        goodput_config_dict={},
+        task_type=TaskType.GENERATION,
+        selected_percentile_metrics=_MEDIA_PERCENTILE_METRICS,
+        max_concurrency=None,
+        request_rate=float("inf"),
+        benchmark_duration=5.0,
+    )
+
+    out = capsys.readouterr().out
+    assert actual_output_lens == [0, 0]
+    assert metrics.total_output == 0
+    assert metrics.max_output_tokens_per_s == 0.0
+    assert " Text Result " not in out
+    assert "Peak output token throughput" not in out
+    assert "Time to First Token" not in out
+    assert " Image Result " in out
+
+
+def test_pure_video_benchmark_omits_text_result(capsys):
+    """Pure video generation must not print Text Result or invent peak tok/s."""
+    outputs = [_make_video_output(63), _make_video_output(63)]
+
+    metrics, actual_output_lens = calculate_metrics(
+        input_requests=[],
+        outputs=outputs,
+        dur_s=10.0,
+        tokenizer=None,
+        selected_percentiles=[99.0],
+        goodput_config_dict={},
+        task_type=TaskType.GENERATION,
+        selected_percentile_metrics=_MEDIA_PERCENTILE_METRICS,
+        max_concurrency=None,
+        request_rate=float("inf"),
+        benchmark_duration=10.0,
+    )
+
+    out = capsys.readouterr().out
+    assert actual_output_lens == [0, 0]
+    assert metrics.total_output == 0
+    assert metrics.max_output_tokens_per_s == 0.0
+    assert " Text Result " not in out
+    assert "Peak output token throughput" not in out
+    assert "Time to First Token" not in out
+    assert " Video Result " in out
+
+
+def test_image_with_generated_text_still_reports_text_result(capsys):
+    """Image edits / AR text alongside images must keep Text Result."""
+    output = _make_image_output(64)
+    output.output_tokens = 8
+    output.generated_text = "revised caption"
+    output.ttft = 0.05
+    output.itl = [0.01] * 7
+
+    calculate_metrics(
+        input_requests=[],
+        outputs=[output],
+        dur_s=3.0,
+        tokenizer=_EmptyAwareTokenizer(),
+        selected_percentiles=[99.0],
+        goodput_config_dict={},
+        task_type=TaskType.GENERATION,
+        selected_percentile_metrics=_MEDIA_PERCENTILE_METRICS,
+        max_concurrency=None,
+        request_rate=float("inf"),
+        benchmark_duration=3.0,
+    )
+
+    out = capsys.readouterr().out
+    assert " Text Result " in out
+    assert "Time to First Token" in out
+    assert " Image Result " in out
+
+
 if __name__ == "__main__":
     pytest.main([__file__, "-v", "-s"])