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

[Feature][Wan2.2] Speed up diffusion model startup by multi-thread weight loading (#1504)

Browse Source 
Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: Samit <285365963@qq.com>
This commit is contained in:
Samit authored and GitHub committed 2026-03-02 14:53:25 +00:00
1 parent a4b2e48718
commit 22a51a7cdb
6 files changed
+57 -22
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

vllm_omni/diffusion/worker/diffusion_model_runner.py
+1 -1
View File
@@ -102,7 +102,7 @@ class DiffusionModelRunner:
# Load model within forward context
load_config = LoadConfig()
model_loader = DiffusersPipelineLoader(load_config)
model_loader = DiffusersPipelineLoader(load_config, od_config=self.od_config)
time_before_load = time.perf_counter()
with get_memory_context():