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

[BugFix] Fix the issue of thinker requests being preempted, causing shape mismatch. (#3147)

Browse Source 
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
This commit is contained in:
amy-why-3459 authored and GitHub committed 2026-05-15 17:07:42 +08:00
1 parent 440c718d2a
commit e7ee5de09f
5 files changed
+65 -74
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/dfx/perf/tests/test_qwen3_omni_async_chunk.json
+5 -5
View File
@@ -10,16 +10,16 @@
"dataset_name": "random",
"backend": "openai-chat-omni",
"endpoint": "/v1/chat/completions",
"num_prompts": [4, 16, 32, 64],
"max_concurrency": [1, 4, 8, 16],
"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],
"mean_audio_ttfp_ms": [1000, 3000, 5000, 7000],
"mean_audio_rtf": [0.2, 0.35, 0.6, 0.85]
"mean_ttft_ms": [1000, 3000, 5000, 7000, 9000],
"mean_audio_ttfp_ms": [1000, 3000, 5000, 7000, 9000],
"mean_audio_rtf": [0.2, 0.35, 0.6, 0.85, 0.9]
}
},
{
tests/e2e/online_serving/test_qwen3_omni_expansion.py
+7 -2
View File
@@ -44,7 +44,7 @@ def get_batch_token_config(default_path):
return modify_stage_config(
default_path,
updates={
"stages": {1: {"max_num_batched_tokens": 64}},
"stages": {0: {"max_num_batched_tokens": 64}, 1: {"max_num_batched_tokens": 64}},
},
)
@@ -95,7 +95,12 @@ test_params = [
test_token_params = [
pytest.param(
OmniServerParams(model=model, stage_config_path=get_batch_token_config(default_path), use_stage_cli=True),
OmniServerParams(
model=model,
stage_config_path=get_batch_token_config(default_path),
use_stage_cli=True,
server_args=["--async-chunk"],
),
id="batch_token_64",
)
]