diff --git a/.buildkite/test-nightly.yml b/.buildkite/test-nightly.yml
index f46e17aec..66e03d5c7 100644
--- a/.buildkite/test-nightly.yml
+++ b/.buildkite/test-nightly.yml
@@ -169,14 +169,104 @@ steps:
                       path: /mnt/hf-cache
                       type: DirectoryOrCreate
 
-      - label: ":full_moon: Omni · Perf Test"
-        key: nightly-omni-performance
+      - label: ":full_moon: Omni · Perf Test · No Async Chunk"
+        key: nightly-omni-performance-no-async-chunk
         timeout_in_minutes: 180
         commands:
           - export BENCHMARK_DIR=tests/dfx/perf/results
           - |
             set +e
-            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen_omni.json
+            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen3_omni_no_async_chunk.json
+            EXIT=$$?
+            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
+            exit $$EXIT
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 2
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: ":full_moon: Omni · Perf Test · Async Chunk"
+        key: nightly-omni-performance-async-chunk
+        timeout_in_minutes: 180
+        commands:
+          - export BENCHMARK_DIR=tests/dfx/perf/results
+          - |
+            set +e
+            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen3_omni_async_chunk.json
+            EXIT=$$?
+            buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
+            exit $$EXIT
+        agents:
+          queue: "mithril-h100-pool"
+        plugins:
+          - kubernetes:
+              podSpec:
+                containers:
+                  - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                    resources:
+                      limits:
+                        nvidia.com/gpu: 2
+                    volumeMounts:
+                      - name: devshm
+                        mountPath: /dev/shm
+                      - name: hf-cache
+                        mountPath: /root/.cache/huggingface
+                    env:
+                      - name: HF_HOME
+                        value: /root/.cache/huggingface
+                      - name: HF_TOKEN
+                        valueFrom:
+                          secretKeyRef:
+                            name: hf-token-secret
+                            key: token
+                nodeSelector:
+                  node.kubernetes.io/instance-type: gpu-h100-sxm
+                volumes:
+                  - name: devshm
+                    emptyDir:
+                      medium: Memory
+                  - name: hf-cache
+                    hostPath:
+                      path: /mnt/hf-cache
+                      type: DirectoryOrCreate
+
+      - label: ":full_moon: Omni · Perf Test · vLLM Text"
+        key: nightly-omni-performance-vllm-text
+        timeout_in_minutes: 180
+        commands:
+          - export BENCHMARK_DIR=tests/dfx/perf/results
+          - |
+            set +e
+            pytest -s -v tests/dfx/perf/scripts/run_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen3_omni_vllm_text.json
             EXIT=$$?
             buildkite-agent artifact upload "tests/dfx/perf/results/*.json"
             exit $$EXIT
@@ -1176,7 +1266,9 @@ steps:
   - label: ":email: Nightly Collection & Email"
     key: nightly-perf-distribution
     depends_on:
-      - nightly-omni-performance
+      - nightly-omni-performance-no-async-chunk
+      - nightly-omni-performance-async-chunk
+      - nightly-omni-performance-vllm-text
       - nightly-tts-performance
       - nightly-diffusion-x2iat-performance-qwen-image
       - nightly-diffusion-x2iat-performance-qwen-image-edit
@@ -1190,7 +1282,9 @@ steps:
       - export DEFAULT_INPUT_DIR=tests/dfx/perf/results
       - export DEFAULT_OUTPUT_DIR=tests/dfx/perf/results
       - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-tts-performance
-      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-omni-performance
+      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-omni-performance-no-async-chunk
+      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-omni-performance-async-chunk
+      - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-omni-performance-vllm-text
       - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-diffusion-x2iat-performance-qwen-image
       - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-diffusion-x2iat-performance-qwen-image-edit
       - buildkite-agent artifact download "tests/dfx/perf/results/*.json" . --step nightly-diffusion-x2iat-performance-qwen-image-edit-2509
diff --git a/.gitignore b/.gitignore
index bf5e28510..378de441c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -239,6 +239,7 @@ data/
 datasets/
 *.csv
 *.json
+!tests/dfx/perf/tests/*.json
 !apps/ComfyUI-vLLM-Omni/example_workflows/*.json
 *.jsonl
 *.parquet
diff --git a/tests/dfx/perf/tests/test_qwen3_omni_async_chunk.json b/tests/dfx/perf/tests/test_qwen3_omni_async_chunk.json
new file mode 100644
index 000000000..4f73f2b6a
--- /dev/null
+++ b/tests/dfx/perf/tests/test_qwen3_omni_async_chunk.json
@@ -0,0 +1,209 @@
+[
+    {
+        "test_name": "test_qwen3_omni_chunk",
+        "server_params": {
+            "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
+            "extra_cli_args": ["--async-chunk"]
+        },
+        "benchmark_params": [
+            {
+                "dataset_name": "random",
+                "backend": "openai-chat-omni",
+                "endpoint": "/v1/chat/completions",
+                "num_prompts": [4, 16, 32, 64],
+                "max_concurrency": [1, 4, 8, 16],
+                "random_input_len": 2500,
+                "random_output_len": 900,
+                "ignore_eos": true,
+                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
+                "baseline": {
+                    "mean_ttft_ms": [1000, 3000, 5000, 7000],
+                    "mean_audio_ttfp_ms": [1000, 3000, 5000, 7000],
+                    "mean_audio_rtf": [0.2, 0.35, 0.6, 0.85]
+                }
+            },
+            {
+                "dataset_name": "random-mm",
+                "backend": "openai-chat-omni",
+                "endpoint": "/v1/chat/completions",
+                "num_prompts": [10],
+                "request_rate": [0.1],
+                "random_input_len": 100,
+                "random_output_len": 100,
+                "random_range_ratio": 0.0,
+                "ignore_eos": true,
+                "random_mm_base_items_per_request": 1,
+                "random_mm_num_mm_items_range_ratio": 0.5,
+                "random_mm_limit_mm_per_prompt": {
+                    "audio": 1
+                },
+                "random_mm_bucket_config": {
+                    "(0, 60, 3)": 1.0
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
+                "baseline": {
+                    "mean_ttft_ms": [2000],
+                    "mean_audio_ttfp_ms": [2000],
+                    "mean_audio_rtf": [0.25]
+                }
+            },
+            {
+                "dataset_name": "random-mm",
+                "backend": "openai-chat-omni",
+                "endpoint": "/v1/chat/completions",
+                "num_prompts": [40],
+                "request_rate": [0.5],
+                "random_input_len": 100,
+                "random_output_len": 100,
+                "random_range_ratio": 0.0,
+                "ignore_eos": true,
+                "random_mm_base_items_per_request": 2,
+                "random_mm_num_mm_items_range_ratio": 0.5,
+                "random_mm_limit_mm_per_prompt": {
+                    "image": 1,
+                    "video": 1
+                },
+                "random_mm_bucket_config": {
+                    "(256, 256, 1)": 0.5,
+                    "(720, 1280, 2)": 0.5
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
+                "baseline": {
+                    "mean_ttft_ms": [6000],
+                    "mean_audio_ttfp_ms": [6000],
+                    "mean_audio_rtf": [0.7]
+                }
+            },
+            {
+                "dataset_name": "random-mm",
+                "backend": "openai-chat-omni",
+                "endpoint": "/v1/chat/completions",
+                "num_prompts": [100],
+                "request_rate": [1.0],
+                "random_input_len": 100,
+                "random_output_len": 100,
+                "random_range_ratio": 0.0,
+                "ignore_eos": true,
+                "random_mm_base_items_per_request": 3,
+                "random_mm_num_mm_items_range_ratio": 0.5,
+                "random_mm_limit_mm_per_prompt": {
+                    "image": 1,
+                    "video": 1,
+                    "audio": 1
+                },
+                "random_mm_bucket_config": {
+                    "(256, 256, 1)": 0.34,
+                    "(720, 1280, 2)": 0.33,
+                    "(0, 60, 3)": 0.33
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
+                "baseline": {
+                    "mean_ttft_ms": [12000],
+                    "mean_audio_ttfp_ms": [12000],
+                    "mean_audio_rtf": [1.0]
+                }
+            },
+            {
+                "dataset_name": "random",
+                "backend": "openai-chat-omni",
+                "endpoint": "/v1/chat/completions",
+                "num_prompts": [4, 16, 32, 64, 128],
+                "max_concurrency": [1, 4, 8, 16, 32],
+                "random_input_len": 2500,
+                "random_output_len": 900,
+                "ignore_eos": true,
+                "extra_body": {
+                    "modalities": ["text"]
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el",
+                "baseline": {
+                    "mean_ttft_ms": [1000, 3000, 5000, 7000, 9000]
+                }
+            },
+            {
+                "dataset_name": "random-mm",
+                "backend": "openai-chat-omni",
+                "endpoint": "/v1/chat/completions",
+                "num_prompts": [10],
+                "request_rate": [0.1],
+                "random_input_len": 100,
+                "random_output_len": 100,
+                "random_range_ratio": 0.0,
+                "ignore_eos": true,
+                "extra_body": {
+                    "modalities": ["text"]
+                },
+                "random_mm_base_items_per_request": 1,
+                "random_mm_num_mm_items_range_ratio": 0.5,
+                "random_mm_limit_mm_per_prompt": {
+                    "audio": 1
+                },
+                "random_mm_bucket_config": {
+                    "(0, 60, 3)": 1.0
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el",
+                "baseline": {
+                    "mean_ttft_ms": [2000]
+                }
+            },
+            {
+                "dataset_name": "random-mm",
+                "backend": "openai-chat-omni",
+                "endpoint": "/v1/chat/completions",
+                "num_prompts": [40],
+                "request_rate": [0.5],
+                "random_input_len": 100,
+                "random_output_len": 100,
+                "random_range_ratio": 0.0,
+                "ignore_eos": true,
+                "extra_body": {
+                    "modalities": ["text"]
+                },
+                "random_mm_base_items_per_request": 2,
+                "random_mm_num_mm_items_range_ratio": 0.5,
+                "random_mm_limit_mm_per_prompt": {
+                    "image": 1,
+                    "video": 1
+                },
+                "random_mm_bucket_config": {
+                    "(256, 256, 1)": 0.5,
+                    "(720, 1280, 2)": 0.5
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el",
+                "baseline": {
+                    "mean_ttft_ms": [6000]
+                }
+            },
+            {
+                "dataset_name": "random-mm",
+                "backend": "openai-chat-omni",
+                "endpoint": "/v1/chat/completions",
+                "num_prompts": [100],
+                "request_rate": [1.0],
+                "random_input_len": 100,
+                "random_output_len": 100,
+                "random_range_ratio": 0.0,
+                "ignore_eos": true,
+                "extra_body": {
+                    "modalities": ["text"]
+                },
+                "random_mm_base_items_per_request": 3,
+                "random_mm_num_mm_items_range_ratio": 0.5,
+                "random_mm_limit_mm_per_prompt": {
+                    "image": 1,
+                    "video": 1,
+                    "audio": 1
+                },
+                "random_mm_bucket_config": {
+                    "(256, 256, 1)": 0.34,
+                    "(720, 1280, 2)": 0.33,
+                    "(0, 60, 3)": 0.33
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el",
+                "baseline": {
+                    "mean_ttft_ms": [6000]
+                }
+            }
+        ]
+    }
+]
diff --git a/tests/dfx/perf/tests/test_qwen3_omni_no_async_chunk.json b/tests/dfx/perf/tests/test_qwen3_omni_no_async_chunk.json
new file mode 100644
index 000000000..b91a8a89b
--- /dev/null
+++ b/tests/dfx/perf/tests/test_qwen3_omni_no_async_chunk.json
@@ -0,0 +1,108 @@
+[
+    {
+        "test_name": "test_qwen3_omni",
+        "server_params": {
+            "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
+            "extra_cli_args": ["--no-async-chunk"]
+        },
+        "benchmark_params": [
+            {
+                "dataset_name": "random",
+                "backend": "openai-chat-omni",
+                "endpoint": "/v1/chat/completions",
+                "num_prompts": [4, 16, 32, 64, 128],
+                "max_concurrency": [1, 4, 8, 16, 32],
+                "random_input_len": 2500,
+                "random_output_len": 900,
+                "ignore_eos": true,
+                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
+                "baseline": {
+                    "mean_ttft_ms": [1000, 3000, 5000, 7000, 9000],
+                    "mean_audio_ttfp_ms": [30000, 60000, 90000, 120000, 150000],
+                    "mean_audio_rtf": [0.35, 0.45, 0.55, 0.65, 0.75]
+                }
+            },
+            {
+                "dataset_name": "random-mm",
+                "backend": "openai-chat-omni",
+                "endpoint": "/v1/chat/completions",
+                "num_prompts": [10],
+                "request_rate": [0.1],
+                "random_input_len": 100,
+                "random_output_len": 100,
+                "random_range_ratio": 0.0,
+                "ignore_eos": true,
+                "random_mm_base_items_per_request": 1,
+                "random_mm_num_mm_items_range_ratio": 0.5,
+                "random_mm_limit_mm_per_prompt": {
+                    "audio": 1
+                },
+                "random_mm_bucket_config": {
+                    "(0, 60, 3)": 1.0
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
+                "baseline": {
+                    "mean_ttft_ms": [2000],
+                    "mean_audio_ttfp_ms": [10000],
+                    "mean_audio_rtf": [0.25]
+                }
+            },
+            {
+                "dataset_name": "random-mm",
+                "backend": "openai-chat-omni",
+                "endpoint": "/v1/chat/completions",
+                "num_prompts": [40],
+                "request_rate": [0.5],
+                "random_input_len": 100,
+                "random_output_len": 100,
+                "random_range_ratio": 0.0,
+                "ignore_eos": true,
+                "random_mm_base_items_per_request": 2,
+                "random_mm_num_mm_items_range_ratio": 0.5,
+                "random_mm_limit_mm_per_prompt": {
+                    "image": 1,
+                    "video": 1
+                },
+                "random_mm_bucket_config": {
+                    "(256, 256, 1)": 0.5,
+                    "(720, 1280, 2)": 0.5
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
+                "baseline": {
+                    "mean_ttft_ms": [6000],
+                    "mean_audio_ttfp_ms": [15000],
+                    "mean_audio_rtf": [0.45]
+                }
+            },
+            {
+                "dataset_name": "random-mm",
+                "backend": "openai-chat-omni",
+                "endpoint": "/v1/chat/completions",
+                "num_prompts": [100],
+                "request_rate": [1.0],
+                "random_input_len": 100,
+                "random_output_len": 100,
+                "random_range_ratio": 0.0,
+                "ignore_eos": true,
+                "random_mm_base_items_per_request": 3,
+                "random_mm_num_mm_items_range_ratio": 0.5,
+                "random_mm_limit_mm_per_prompt": {
+                    "image": 1,
+                    "video": 1,
+                    "audio": 1
+                },
+                "random_mm_bucket_config": {
+                    "(256, 256, 1)": 0.34,
+                    "(720, 1280, 2)": 0.33,
+                    "(0, 60, 3)": 0.33
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
+                "baseline": {
+                    "mean_ttft_ms": [12000],
+                    "mean_audio_ttfp_ms": [18000],
+                    "mean_audio_rtf": [0.9]
+                }
+            }
+        ]
+    }
+]
diff --git a/tests/dfx/perf/tests/test_qwen3_omni_vllm_text.json b/tests/dfx/perf/tests/test_qwen3_omni_vllm_text.json
new file mode 100644
index 000000000..aa2f79033
--- /dev/null
+++ b/tests/dfx/perf/tests/test_qwen3_omni_vllm_text.json
@@ -0,0 +1,137 @@
+[
+    {
+        "test_name": "test_qwen3_omni_vllm_text",
+        "server_params": {
+            "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
+            "use_omni": false,
+            "extra_cli_args": ["--no-enable-prefix-caching"]
+        },
+        "benchmark_params": [
+            {
+                "dataset_name": "random",
+                "backend": "vllm",
+                "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
+                "endpoint": "/v1/completions",
+                "num_prompts": [4, 16, 32, 64, 128],
+                "max_concurrency": [1, 4, 8, 16, 32],
+                "random_input_len": 2500,
+                "random_output_len": 900,
+                "temperature": 0.4,
+                "top_p": 0.9,
+                "top_k": 1,
+                "seed": 42,
+                "repetition_penalty": 1.05,
+                "ignore_eos": true,
+                "extra_body": {
+                    "modalities": ["text"]
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el",
+                "baseline": {
+                    "mean_ttft_ms": [1000, 3000, 5000, 7000, 9000]
+                }
+            },
+            {
+                "dataset_name": "random-mm",
+                "backend": "vllm",
+                "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
+                "endpoint": "/v1/completions",
+                "num_prompts": [10],
+                "request_rate": [0.1],
+                "random_input_len": 100,
+                "random_output_len": 100,
+                "random_range_ratio": 0.0,
+                "temperature": 0.4,
+                "top_p": 0.9,
+                "top_k": 1,
+                "seed": 42,
+                "repetition_penalty": 1.05,
+                "ignore_eos": true,
+                "extra_body": {
+                    "modalities": ["text"]
+                },
+                "random_mm_base_items_per_request": 1,
+                "random_mm_num_mm_items_range_ratio": 0.5,
+                "random_mm_limit_mm_per_prompt": {
+                    "audio": 1
+                },
+                "random_mm_bucket_config": {
+                    "(0, 60, 3)": 1.0
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el",
+                "baseline": {
+                    "mean_ttft_ms": [2000]
+                }
+            },
+            {
+                "dataset_name": "random-mm",
+                "backend": "vllm",
+                "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
+                "endpoint": "/v1/completions",
+                "num_prompts": [40],
+                "request_rate": [0.5],
+                "random_input_len": 100,
+                "random_output_len": 100,
+                "random_range_ratio": 0.0,
+                "temperature": 0.4,
+                "top_p": 0.9,
+                "top_k": 1,
+                "seed": 42,
+                "repetition_penalty": 1.05,
+                "ignore_eos": true,
+                "extra_body": {
+                    "modalities": ["text"]
+                },
+                "random_mm_base_items_per_request": 2,
+                "random_mm_num_mm_items_range_ratio": 0.5,
+                "random_mm_limit_mm_per_prompt": {
+                    "image": 1,
+                    "video": 1
+                },
+                "random_mm_bucket_config": {
+                    "(256, 256, 1)": 0.5,
+                    "(720, 1280, 2)": 0.5
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el",
+                "baseline": {
+                    "mean_ttft_ms": [6000]
+                }
+            },
+            {
+                "dataset_name": "random-mm",
+                "backend": "vllm",
+                "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
+                "endpoint": "/v1/completions",
+                "num_prompts": [100],
+                "request_rate": [1.0],
+                "random_input_len": 100,
+                "random_output_len": 100,
+                "random_range_ratio": 0.0,
+                "temperature": 0.4,
+                "top_p": 0.9,
+                "top_k": 1,
+                "seed": 42,
+                "repetition_penalty": 1.05,
+                "ignore_eos": true,
+                "extra_body": {
+                    "modalities": ["text"]
+                },
+                "random_mm_base_items_per_request": 3,
+                "random_mm_num_mm_items_range_ratio": 0.5,
+                "random_mm_limit_mm_per_prompt": {
+                    "image": 1,
+                    "video": 1,
+                    "audio": 1
+                },
+                "random_mm_bucket_config": {
+                    "(256, 256, 1)": 0.34,
+                    "(720, 1280, 2)": 0.33,
+                    "(0, 60, 3)": 0.33
+                },
+                "percentile-metrics": "ttft,tpot,itl,e2el",
+                "baseline": {
+                    "mean_ttft_ms": [6000]
+                }
+            }
+        ]
+    }
+]
diff --git a/tests/dfx/perf/tests/test_qwen_omni.json b/tests/dfx/perf/tests/test_qwen_omni.json
deleted file mode 100644
index 3c70e027c..000000000
--- a/tests/dfx/perf/tests/test_qwen_omni.json
+++ /dev/null
@@ -1,450 +0,0 @@
-[
-    {
-        "test_name": "test_qwen3_omni",
-        "server_params": {
-            "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
-            "extra_cli_args": ["--no-async-chunk"]
-        },
-        "benchmark_params": [
-            {
-                "dataset_name": "random",
-                "backend": "openai-chat-omni",
-                "endpoint": "/v1/chat/completions",
-                "num_prompts": [4, 16, 32, 64, 128],
-                "max_concurrency": [1, 4, 8, 16, 32],
-                "random_input_len": 2500,
-                "random_output_len": 900,
-                "ignore_eos": true,
-                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
-                "baseline": {
-                    "mean_ttft_ms": [1000, 3000, 5000, 7000, 9000],
-                    "mean_audio_ttfp_ms": [30000, 60000, 90000, 120000, 150000],
-                    "mean_audio_rtf": [0.35, 0.45, 0.55, 0.65, 0.75]
-                }
-            },
-            {
-                "dataset_name": "random-mm",
-                "backend": "openai-chat-omni",
-                "endpoint": "/v1/chat/completions",
-                "num_prompts": [10],
-                "request_rate": [0.1],
-                "random_input_len": 100,
-                "random_output_len": 100,
-                "random_range_ratio": 0.0,
-                "ignore_eos": true,
-                "random_mm_base_items_per_request": 1,
-                "random_mm_num_mm_items_range_ratio": 0.5,
-                "random_mm_limit_mm_per_prompt": {
-                    "audio": 1
-                },
-                "random_mm_bucket_config": {
-                    "(0, 60, 3)": 1.0
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
-                "baseline": {
-                    "mean_ttft_ms": [2000],
-                    "mean_audio_ttfp_ms": [10000],
-                    "mean_audio_rtf": [0.25]
-                }
-            },
-            {
-                "dataset_name": "random-mm",
-                "backend": "openai-chat-omni",
-                "endpoint": "/v1/chat/completions",
-                "num_prompts": [40],
-                "request_rate": [0.5],
-                "random_input_len": 100,
-                "random_output_len": 100,
-                "random_range_ratio": 0.0,
-                "ignore_eos": true,
-                "random_mm_base_items_per_request": 2,
-                "random_mm_num_mm_items_range_ratio": 0.5,
-                "random_mm_limit_mm_per_prompt": {
-                    "image": 1,
-                    "video": 1
-                },
-                "random_mm_bucket_config": {
-                    "(256, 256, 1)": 0.5,
-                    "(720, 1280, 2)": 0.5
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
-                "baseline": {
-                    "mean_ttft_ms": [6000],
-                    "mean_audio_ttfp_ms": [15000],
-                    "mean_audio_rtf": [0.45]
-                }
-            },
-            {
-                "dataset_name": "random-mm",
-                "backend": "openai-chat-omni",
-                "endpoint": "/v1/chat/completions",
-                "num_prompts": [100],
-                "request_rate": [1.0],
-                "random_input_len": 100,
-                "random_output_len": 100,
-                "random_range_ratio": 0.0,
-                "ignore_eos": true,
-                "random_mm_base_items_per_request": 3,
-                "random_mm_num_mm_items_range_ratio": 0.5,
-                "random_mm_limit_mm_per_prompt": {
-                    "image": 1,
-                    "video": 1,
-                    "audio": 1
-                },
-                "random_mm_bucket_config": {
-                    "(256, 256, 1)": 0.34,
-                    "(720, 1280, 2)": 0.33,
-                    "(0, 60, 3)": 0.33
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
-                "baseline": {
-                    "mean_ttft_ms": [12000],
-                    "mean_audio_ttfp_ms": [18000],
-                    "mean_audio_rtf": [0.9]
-                }
-            }
-        ]
-    },
-    {
-        "test_name": "test_qwen3_omni_chunk",
-        "server_params": {
-            "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
-            "extra_cli_args": ["--async-chunk"]
-        },
-        "benchmark_params": [
-            {
-                "dataset_name": "random",
-                "backend": "openai-chat-omni",
-                "endpoint": "/v1/chat/completions",
-                "num_prompts": [4, 16, 32, 64],
-                "max_concurrency": [1, 4, 8, 16],
-                "random_input_len": 2500,
-                "random_output_len": 900,
-                "ignore_eos": true,
-                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
-                "baseline": {
-                    "mean_ttft_ms": [1000, 3000, 5000, 7000],
-                    "mean_audio_ttfp_ms": [1000, 3000, 5000, 7000],
-                    "mean_audio_rtf": [0.2, 0.35, 0.6, 0.85]
-                }
-            },
-            {
-                "dataset_name": "random-mm",
-                "backend": "openai-chat-omni",
-                "endpoint": "/v1/chat/completions",
-                "num_prompts": [10],
-                "request_rate": [0.1],
-                "random_input_len": 100,
-                "random_output_len": 100,
-                "random_range_ratio": 0.0,
-                "ignore_eos": true,
-                "random_mm_base_items_per_request": 1,
-                "random_mm_num_mm_items_range_ratio": 0.5,
-                "random_mm_limit_mm_per_prompt": {
-                    "audio": 1
-                },
-                "random_mm_bucket_config": {
-                    "(0, 60, 3)": 1.0
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
-                "baseline": {
-                    "mean_ttft_ms": [2000],
-                    "mean_audio_ttfp_ms": [2000],
-                    "mean_audio_rtf": [0.25]
-                }
-            },
-            {
-                "dataset_name": "random-mm",
-                "backend": "openai-chat-omni",
-                "endpoint": "/v1/chat/completions",
-                "num_prompts": [40],
-                "request_rate": [0.5],
-                "random_input_len": 100,
-                "random_output_len": 100,
-                "random_range_ratio": 0.0,
-                "ignore_eos": true,
-                "random_mm_base_items_per_request": 2,
-                "random_mm_num_mm_items_range_ratio": 0.5,
-                "random_mm_limit_mm_per_prompt": {
-                    "image": 1,
-                    "video": 1
-                },
-                "random_mm_bucket_config": {
-                    "(256, 256, 1)": 0.5,
-                    "(720, 1280, 2)": 0.5
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
-                "baseline": {
-                    "mean_ttft_ms": [6000],
-                    "mean_audio_ttfp_ms": [6000],
-                    "mean_audio_rtf": [0.7]
-                }
-            },
-            {
-                "dataset_name": "random-mm",
-                "backend": "openai-chat-omni",
-                "endpoint": "/v1/chat/completions",
-                "num_prompts": [100],
-                "request_rate": [1.0],
-                "random_input_len": 100,
-                "random_output_len": 100,
-                "random_range_ratio": 0.0,
-                "ignore_eos": true,
-                "random_mm_base_items_per_request": 3,
-                "random_mm_num_mm_items_range_ratio": 0.5,
-                "random_mm_limit_mm_per_prompt": {
-                    "image": 1,
-                    "video": 1,
-                    "audio": 1
-                },
-                "random_mm_bucket_config": {
-                    "(256, 256, 1)": 0.34,
-                    "(720, 1280, 2)": 0.33,
-                    "(0, 60, 3)": 0.33
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
-                "baseline": {
-                    "mean_ttft_ms": [12000],
-                    "mean_audio_ttfp_ms": [12000],
-                    "mean_audio_rtf": [1.0]
-                }
-            },
-            {
-                "dataset_name": "random",
-                "backend": "openai-chat-omni",
-                "endpoint": "/v1/chat/completions",
-                "num_prompts": [4, 16, 32, 64, 128],
-                "max_concurrency": [1, 4, 8, 16, 32],
-                "random_input_len": 2500,
-                "random_output_len": 900,
-                "ignore_eos": true,
-                "extra_body": {
-                    "modalities": ["text"]
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el",
-                "baseline": {
-                    "mean_ttft_ms": [1000, 3000, 5000, 7000, 9000]
-                }
-            },
-            {
-                "dataset_name": "random-mm",
-                "backend": "openai-chat-omni",
-                "endpoint": "/v1/chat/completions",
-                "num_prompts": [10],
-                "request_rate": [0.1],
-                "random_input_len": 100,
-                "random_output_len": 100,
-                "random_range_ratio": 0.0,
-                "ignore_eos": true,
-                "extra_body": {
-                    "modalities": ["text"]
-                },
-                "random_mm_base_items_per_request": 1,
-                "random_mm_num_mm_items_range_ratio": 0.5,
-                "random_mm_limit_mm_per_prompt": {
-                    "audio": 1
-                },
-                "random_mm_bucket_config": {
-                    "(0, 60, 3)": 1.0
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el",
-                "baseline": {
-                    "mean_ttft_ms": [2000]
-                }
-            },
-            {
-                "dataset_name": "random-mm",
-                "backend": "openai-chat-omni",
-                "endpoint": "/v1/chat/completions",
-                "num_prompts": [40],
-                "request_rate": [0.5],
-                "random_input_len": 100,
-                "random_output_len": 100,
-                "random_range_ratio": 0.0,
-                "ignore_eos": true,
-                "extra_body": {
-                    "modalities": ["text"]
-                },
-                "random_mm_base_items_per_request": 2,
-                "random_mm_num_mm_items_range_ratio": 0.5,
-                "random_mm_limit_mm_per_prompt": {
-                    "image": 1,
-                    "video": 1
-                },
-                "random_mm_bucket_config": {
-                    "(256, 256, 1)": 0.5,
-                    "(720, 1280, 2)": 0.5
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el",
-                "baseline": {
-                    "mean_ttft_ms": [6000]
-                }
-            },
-            {
-                "dataset_name": "random-mm",
-                "backend": "openai-chat-omni",
-                "endpoint": "/v1/chat/completions",
-                "num_prompts": [100],
-                "request_rate": [1.0],
-                "random_input_len": 100,
-                "random_output_len": 100,
-                "random_range_ratio": 0.0,
-                "ignore_eos": true,
-                "extra_body": {
-                    "modalities": ["text"]
-                },
-                "random_mm_base_items_per_request": 3,
-                "random_mm_num_mm_items_range_ratio": 0.5,
-                "random_mm_limit_mm_per_prompt": {
-                    "image": 1,
-                    "video": 1,
-                    "audio": 1
-                },
-                "random_mm_bucket_config": {
-                    "(256, 256, 1)": 0.34,
-                    "(720, 1280, 2)": 0.33,
-                    "(0, 60, 3)": 0.33
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el",
-                "baseline": {
-                    "mean_ttft_ms": [6000]
-                }
-            }
-        ]
-    },
-    {
-        "test_name": "test_qwen3_omni_vllm_text",
-        "server_params": {
-            "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
-            "use_omni": false,
-            "extra_cli_args": ["--no-enable-prefix-caching"]
-        },
-        "benchmark_params": [
-            {
-                "dataset_name": "random",
-                "backend": "vllm",
-                "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
-                "endpoint": "/v1/completions",
-                "num_prompts": [4, 16, 32, 64, 128],
-                "max_concurrency": [1, 4, 8, 16, 32],
-                "random_input_len": 2500,
-                "random_output_len": 900,
-                "temperature": 0.4,
-                "top_p": 0.9,
-                "top_k": 1,
-                "seed": 42,
-                "repetition_penalty": 1.05,
-                "ignore_eos": true,
-                "extra_body": {
-                    "modalities": ["text"]
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el",
-                "baseline": {
-                    "mean_ttft_ms": [1000, 3000, 5000, 7000, 9000]
-                }
-            },
-            {
-                "dataset_name": "random-mm",
-                "backend": "vllm",
-                "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
-                "endpoint": "/v1/completions",
-                "num_prompts": [10],
-                "request_rate": [0.1],
-                "random_input_len": 100,
-                "random_output_len": 100,
-                "random_range_ratio": 0.0,
-                "temperature": 0.4,
-                "top_p": 0.9,
-                "top_k": 1,
-                "seed": 42,
-                "repetition_penalty": 1.05,
-                "ignore_eos": true,
-                "extra_body": {
-                    "modalities": ["text"]
-                },
-                "random_mm_base_items_per_request": 1,
-                "random_mm_num_mm_items_range_ratio": 0.5,
-                "random_mm_limit_mm_per_prompt": {
-                    "audio": 1
-                },
-                "random_mm_bucket_config": {
-                    "(0, 60, 3)": 1.0
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el",
-                "baseline": {
-                    "mean_ttft_ms": [2000]
-                }
-            },
-            {
-                "dataset_name": "random-mm",
-                "backend": "vllm",
-                "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
-                "endpoint": "/v1/completions",
-                "num_prompts": [40],
-                "request_rate": [0.5],
-                "random_input_len": 100,
-                "random_output_len": 100,
-                "random_range_ratio": 0.0,
-                "temperature": 0.4,
-                "top_p": 0.9,
-                "top_k": 1,
-                "seed": 42,
-                "repetition_penalty": 1.05,
-                "ignore_eos": true,
-                "extra_body": {
-                    "modalities": ["text"]
-                },
-                "random_mm_base_items_per_request": 2,
-                "random_mm_num_mm_items_range_ratio": 0.5,
-                "random_mm_limit_mm_per_prompt": {
-                    "image": 1,
-                    "video": 1
-                },
-                "random_mm_bucket_config": {
-                    "(256, 256, 1)": 0.5,
-                    "(720, 1280, 2)": 0.5
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el",
-                "baseline": {
-                    "mean_ttft_ms": [6000]
-                }
-            },
-            {
-                "dataset_name": "random-mm",
-                "backend": "vllm",
-                "model": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
-                "endpoint": "/v1/completions",
-                "num_prompts": [100],
-                "request_rate": [1.0],
-                "random_input_len": 100,
-                "random_output_len": 100,
-                "random_range_ratio": 0.0,
-                "temperature": 0.4,
-                "top_p": 0.9,
-                "top_k": 1,
-                "seed": 42,
-                "repetition_penalty": 1.05,
-                "ignore_eos": true,
-                "extra_body": {
-                    "modalities": ["text"]
-                },
-                "random_mm_base_items_per_request": 3,
-                "random_mm_num_mm_items_range_ratio": 0.5,
-                "random_mm_limit_mm_per_prompt": {
-                    "image": 1,
-                    "video": 1,
-                    "audio": 1
-                },
-                "random_mm_bucket_config": {
-                    "(256, 256, 1)": 0.34,
-                    "(720, 1280, 2)": 0.33,
-                    "(0, 60, 3)": 0.33
-                },
-                "percentile-metrics": "ttft,tpot,itl,e2el",
-                "baseline": {
-                    "mean_ttft_ms": [6000]
-                }
-            }
-        ]
-    }
-]