>>108641945
Am I the only one experiencing looping in gemma 4?
commit="82764d8f405ff7928c061d8c100b50e9f77939f6" && \
model_folder="/mnt/AI/LLM/gemma-4-26B-A4B-it-GGUF/" && \
model_basename="google_gemma-4-26B-A4B-it-Q8_0" && \
mmproj_name="mmproj-google_gemma-4-26B-A4B-it-f16.gguf" && \
model_parameters="--temp 0.6 --top_p 0.95 --top_k 64" && \
model=$model_folder$model_basename'.gguf' && \
cxt_size=$((1 << 15)) && \
CUDA_VISIBLE_DEVICES=0 \
numactl --physcpubind=24-31 --membind=1 \
\
"$HOME/LLAMA_CPP/$commit/llama.cpp/build/bin/llama-server" \
--model "$model" $model_parameters \
--threads $(lscpu | grep "Core(s) per socket" | awk '{print $4}') \
--ctx-size $cxt_size \
--n-gpu-layers 99 \
--no-warmup \
--mmproj $model_folder$mmproj_name \
--port 8001 \
--cache-type-k q8_0 \
--cache-type-v q8_0 \
--flash-attn on \
--image-max-tokens 1120 \
--batch-size $((1024 * 2)) \
--ubatch-size $((1024 * 2)) \
--chat-template-file "/mnt/AI/LLM/gemma-4-26B-A4B-it-GGUF/chat_template.jinja" \
--media-path /tmp \
--n-cpu-moe 10
