llama.cpp Monitor Connecting...
GPU 0: RTX 4090 D (49 GB)
GPU 1: RTX 3090 (24 GB)
Model: Qwen3.6-35B-A3B-UD-Q8_K_XL
GPU 0: RTX 4090 D
VRAM-- / 49140 MB
Utilization--%
Power-- W / 425 W
Temp--°C
GPU 1: RTX 3090
VRAM-- / 24576 MB
Utilization--%
Power-- W / 300 W
Temp--°C
Task Slots
Slot 0
idle
--
--
generated tokens
⚠ Checkpoint restored
Parse tokens: --
Tokens in task: --
Total: --
Max: --
Deferred: --
Slot 1
idle
--
--
generated tokens
⚠ Checkpoint restored
Parse tokens: --
Tokens in task: --
Total: --
Max: --
Deferred: --
KV Cache Status
Prompts0
Used0 / 8000 MiB
Swap Time0 ms
Context524288 tokens
Busy Slots--
Cache Checkpoint Events
Checkpoint Erased0
Checkpoint Missing0
Checkpoint Restored0
Partial seq_rm Failed0
Cache Swaps0
Avg Swap Time0 ms
Max Swap Time0 ms