diff --git a/scripts/serve-frank-large.sh b/scripts/serve-frank-large.sh index 2b18ac5..a114a0b 100755 --- a/scripts/serve-frank-large.sh +++ b/scripts/serve-frank-large.sh @@ -50,7 +50,7 @@ fi : "${PARALLEL_SLOTS:=1}" : "${SPEC_DRAFT_N_MAX:=4}" : "${COMPATIBILITY_MODE:=1}" -: "${CACHE_RAM:=8192}" +TEMPLATE_FILE="${TEMPLATE_FILE:-$SCRIPT_DIR/../dankserver/frank-medium/qwen-sharp-v22.4.0.jinja}" SERVER_BIN="$RUNTIME_DIR/bin/llama-server" MODEL_FILE="$MODEL_DIR/Qwen3.8-27B-IU4-Kairic-Edge.gguf" @@ -113,6 +113,7 @@ ARGS=( -m "$MODEL_FILE" --alias frank-large --host "$HOST" --port "$PORT" --jinja --chat-template-kwargs '{"preserve_thinking":true}' + --chat-template-file "$TEMPLATE_FILE" -dev ROCm0 -ngl 999 -c "$CONTEXT_SIZE" -b 2048 -ub 512 -fa on -ctk f16 -ctv f16 -t 16 -tb 32 -np "$PARALLEL_SLOTS" -ctxcp 32 --cache-ram "$CACHE_RAM"