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

docs: document distributed layerwise offload compatibility (#5839)

Browse Source 
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Hongsheng Liu authored and GitHub committed 2026-08-06 23:21:43 +08:00
1 parent 4b625d1175
commit 62bf8d630d
14 files changed
+471 -95
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/contributing/model/adding_diffusion_model.md
+1 -1
View File
@@ -824,7 +824,7 @@ omni = Omni(model="your-model",
### CPU Offload
See detailed guide: [CPU Offloading for Diffusion Models](../../user_guide/diffusion/cpu_offload_diffusion.md)
See detailed guide: [CPU Offloading for Diffusion Models](../../user_guide/diffusion/cpu_offload.md)
vLLM-Omni provides two offloading strategies to reduce GPU memory usage: