c1b919ec4774e2aaff28a98949240c9fd9903ee4
Condition maxSlotsPerGpu Behavior OptimizeModelStr 0 Bypass: non-shared temporary engine 1 GPU 1 Single slot, no round-robin >1 GPU, VRAM < 24 GB 1 Round-robin: 1 slot per GPU >1 GPU, VRAM >= 24 GB -1 Elastic: on-demand slot growth
Description
No description provided
Languages
C
57.2%
C++
41.8%
Python
0.3%
Objective-C++
0.3%
CMake
0.2%
Other
0.1%