Tuan Nghia Nguyen
c1b919ec47
Fix setting GPU behaviour:
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
2026-03-30 09:59:09 +11:00
..
2026-03-29 22:51:39 +11:00
2026-03-29 22:51:39 +11:00
2026-03-30 09:59:09 +11:00
2026-03-28 19:56:39 +11:00
2026-03-30 09:59:09 +11:00
2026-03-28 19:56:39 +11:00
2026-03-30 09:59:09 +11:00
2026-03-28 19:56:39 +11:00
2026-03-30 09:59:09 +11:00