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

[Refactor][OutputProcessor 2/8]: OmniRequestOutput should inherit RequestOutput and no nested wrap-up (#5146)

Browse Source 
Signed-off-by: Boao Shi <aoibosh@connect.hku.hk>
Signed-off-by: bowieshi <aoibosh@connect.hku.hk>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: R2-Y <ruiruyang2@gmail.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Signed-off-by: Shi Boao Bowie <aoibosh@connect.hku.hk>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: ruirui(rein) yang <73573651+R2-Y@users.noreply.github.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Shi Boao Bowie汪志鹏ruirui yangamy-why-3459Gao HanHongsheng Liu
 authored and GitHub committed 2026-08-12 22:58:23 +08:00
1 parent 38a2500bdf
commit fcf1085395
89 files changed
+944 -639
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/diffusion/offloader/test_diffusion_cpu_offload.py
+2 -2
View File
@@ -122,8 +122,8 @@ def test_cpu_offload_diffusion_model(model_name: str):
print(f"No offload peak memory: {no_offload_peak_memory} MB")
if model_name == "stabilityai/stable-audio-open-1.0":
audio_offload = output_offload[0].request_output.multimodal_output.get("audio")
audio_no_offload = output_no_offload[0].request_output.multimodal_output.get("audio")
audio_offload = output_offload[0].multimodal_output.get("audio")
audio_no_offload = output_no_offload[0].multimodal_output.get("audio")
check_audio_determinism(audio_offload, audio_no_offload, atol=1e-2)
# Set platform-specific VRAM saving thresholds to account