anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Tests] Modify test cases (#2991)

Browse Source 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
This commit is contained in:
amy-why-3459 authored and GitHub committed 2026-04-22 19:08:10 +08:00
1 parent 9d1392dcfc
commit 9337bec9ad
2 files changed
+33 -32
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/dfx/perf/tests/test_qwen_omni.json
+32 -32
View File
@@ -10,16 +10,16 @@
"dataset_name": "random",
"backend": "openai-chat-omni",
"endpoint": "/v1/chat/completions",
"num_prompts": [4, 16, 40],
"max_concurrency": [1, 4, 10],
"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],
"mean_audio_ttfp_ms": [30000, 60000, 90000],
"mean_audio_rtf": [0.35, 0.45, 0.55]
"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]
}
},
{
@@ -52,7 +52,7 @@
"backend": "openai-chat-omni",
"endpoint": "/v1/chat/completions",
"num_prompts": [40],
"request_rate": [0.3],
"request_rate": [0.5],
"random_input_len": 100,
"random_output_len": 100,
"random_range_ratio": 0.0,
@@ -69,9 +69,9 @@
},
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [4000],
"mean_audio_ttfp_ms": [13000],
"mean_audio_rtf": [0.35]
"mean_ttft_ms": [6000],
"mean_audio_ttfp_ms": [15000],
"mean_audio_rtf": [0.45]
}
},
{
@@ -79,7 +79,7 @@
"backend": "openai-chat-omni",
"endpoint": "/v1/chat/completions",
"num_prompts": [100],
"request_rate": [0.5],
"request_rate": [1.0],
"random_input_len": 100,
"random_output_len": 100,
"random_range_ratio": 0.0,
@@ -98,9 +98,9 @@
},
"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]
"mean_ttft_ms": [12000],
"mean_audio_ttfp_ms": [18000],
"mean_audio_rtf": [0.9]
}
}
]
@@ -116,16 +116,16 @@
"dataset_name": "random",
"backend": "openai-chat-omni",
"endpoint": "/v1/chat/completions",
"num_prompts": [4, 16, 40],
"max_concurrency": [1, 4, 10],
"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],
"mean_audio_ttfp_ms": [1000, 3000, 5000],
"mean_audio_rtf": [0.2, 0.35, 0.6]
"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]
}
},
{
@@ -158,7 +158,7 @@
"backend": "openai-chat-omni",
"endpoint": "/v1/chat/completions",
"num_prompts": [40],
"request_rate": [0.3],
"request_rate": [0.5],
"random_input_len": 100,
"random_output_len": 100,
"random_range_ratio": 0.0,
@@ -175,9 +175,9 @@
},
"percentile-metrics": "ttft,tpot,itl,e2el,audio_rtf,audio_ttfp,audio_duration",
"baseline": {
"mean_ttft_ms": [4000],
"mean_audio_ttfp_ms": [4000],
"mean_audio_rtf": [0.4]
"mean_ttft_ms": [6000],
"mean_audio_ttfp_ms": [6000],
"mean_audio_rtf": [0.7]
}
},
{
@@ -185,7 +185,7 @@
"backend": "openai-chat-omni",
"endpoint": "/v1/chat/completions",
"num_prompts": [100],
"request_rate": [0.5],
"request_rate": [1.0],
"random_input_len": 100,
"random_output_len": 100,
"random_range_ratio": 0.0,
@@ -204,17 +204,17 @@
},
"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]
"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, 40],
"max_concurrency": [1, 4, 10],
"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,
@@ -223,7 +223,7 @@
},
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [1000, 3000, 5000]
"mean_ttft_ms": [1000, 3000, 5000, 7000, 9000]
}
},
{
@@ -257,7 +257,7 @@
"backend": "openai-chat-omni",
"endpoint": "/v1/chat/completions",
"num_prompts": [40],
"request_rate": [0.3],
"request_rate": [0.5],
"random_input_len": 100,
"random_output_len": 100,
"random_range_ratio": 0.0,
@@ -277,7 +277,7 @@
},
"percentile-metrics": "ttft,tpot,itl,e2el",
"baseline": {
"mean_ttft_ms": [4000]
"mean_ttft_ms": [6000]
}
},
{
@@ -285,7 +285,7 @@
"backend": "openai-chat-omni",
"endpoint": "/v1/chat/completions",
"num_prompts": [100],
"request_rate": [0.5],
"request_rate": [1.0],
"random_input_len": 100,
"random_output_len": 100,
"random_range_ratio": 0.0,
tests/e2e/online_serving/test_qwen3_omni_expansion.py
+1
View File
@@ -84,6 +84,7 @@ test_params = [
model=model,
stage_config_path=get_async_chunk_config(default_path),
use_stage_cli=True,
server_args=["--async-chunk"],
),
id="async_chunk",
),