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

[BugFix] Fix 'GPUARWorker' attribute error (#5478)

Browse Source 
Signed-off-by: Semmer <semmer@live.cn>
This commit is contained in:
Ting FU authored and GitHub committed 2026-07-28 20:13:33 +08:00
1 parent 12d75cf63a
commit f4640d9a2e
1 file changed
+1
Download Patch File Download Diff File Expand all files Collapse all files
vllm_omni/worker/base.py
+1
View File
@@ -120,6 +120,7 @@ class OmniGPUWorkerBase(GPUWorker):
self.model_runner.profile_run()
self.non_torch_memory = profile_result.non_torch_increase
self.total_consumed = profile_result.total_consumed
self.peak_activation_memory = profile_result.torch_peak_increase
process_memory = (