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

feat(minimax-h3): enable 2x RTX 4090/5090 with DLO (#5764)

Browse Source 
Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>
This commit is contained in:
SYLARandlishunyang12 authored and GitHub committed 2026-08-06 09:02:29 +08:00
1 parent b4581b293b
commit 1c2a81f6d8
28 files changed
+1658 -162
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

vllm_omni/engine/async_omni_engine.py
+1
View File
@@ -1032,6 +1032,7 @@ class AsyncOmniEngine:
"enable_layerwise_offload": kwargs.get("enable_layerwise_offload", False),
"enable_distributed_layerwise_offload": kwargs.get("enable_distributed_layerwise_offload", False),
"dlo_use_allgather": kwargs.get("dlo_use_allgather", True),
"dlo_resident_layers": kwargs.get("dlo_resident_layers", 0),
"enforce_eager": False if kwargs.get("enforce_eager") is None else kwargs.get("enforce_eager"),
"diffusion_compile_granularity": (
"regional"