Variet/variet_llm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: initial project setup with agent guide

Browse Source
This commit is contained in:
Variet-Worker
2026-04-05 00:43:39 +09:00
commit 7890ff6644
1368 changed files with 213076 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
start_gemma4_26b_api.bat Normal file
View File

@@ -0,0 +1,8 @@
@echo off
echo =========================================================
echo Gemma4 26B-A4B API Server (Tuned for Max Speed)
echo [INFO] Tuning VRAM limit correctly to avoid WDDM swap (-ngl 22)
echo =========================================================
echo.
llama_bin_run\llama-server.exe --model models\gemma-4-26B-A4B-it-Q4_K_M.gguf -ngl 22 -c 4096 -np 1 -fa on --cache-type-k q4_0 --cache-type-v q4_0 -ub 512 -b 2048 -t 8 --mlock --prio 2 --port 8000 --host 0.0.0.0
pause