11 lines
607 B
Batchfile
11 lines
607 B
Batchfile
@echo off
|
|
echo =========================================================
|
|
echo Qwen3.5 122B-A10B API Server (MoE Optimized)
|
|
echo [INFO] --cpu-moe: Expert weights forced to CPU RAM
|
|
echo [INFO] -ngl 999: All attention layers on GPU
|
|
echo [INFO] -np 1: Single slot, -c 2048 minimal context
|
|
echo =========================================================
|
|
echo.
|
|
llama_bin_run\llama-server.exe --model models\Q4_K_M\Qwen3.5-122B-A10B-Q4_K_M-00001-of-00003.gguf -ngl 999 --cpu-moe -c 2048 -np 1 -fa on --cache-type-k q4_0 --cache-type-v q4_0 -ub 256 -b 1024 -t 8 --mlock --prio 2 --port 8000 --host 0.0.0.0
|
|
pause
|