#!/usr/bin/env bash
# Benchmark ubatch with llama-bench for frank-large.
#
# This is intentionally a ubatch-only benchmark. It uses one llama-bench
# process, an 8K prompt workload, and equal batch/ubatch values. No server
# process, HTTP requests, or log scraping are used.
#
# Run on Dankclaw after stopping frank-large:
#   sudo systemctl stop frank-large
#   ./scripts/bench-ubatch.sh
#   sudo systemctl start frank-large
set -euo pipefail

: "${LLAMA_BENCH:=/home/dank/GitPackages/ROCmFPX/build-strix-rocmfp4/bin/llama-bench}"
: "${MODEL:=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP/Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf}"
: "${UBATCH_VALUES:=256,512,768,1024,1280,1536,1792,2048,3072,4096}"
: "${CONTEXT:=8192}"
: "${GEN_TOKENS:=128}"
: "${REPETITIONS:=3}"
: "${DEVICE:=ROCm0}"
: "${OUTPUT:=jsonl}"

if [[ ! -x "$LLAMA_BENCH" ]]; then
    printf 'missing executable llama-bench: %s\n' "$LLAMA_BENCH" >&2
    exit 1
fi
if [[ ! -r "$MODEL" ]]; then
    printf 'missing or unreadable model: %s\n' "$MODEL" >&2
    exit 1
fi

exec "$LLAMA_BENCH" \
    --model "$MODEL" \
    --n-prompt "$CONTEXT" \
    --n-gen "$GEN_TOKENS" \
    --batch-size "$UBATCH_VALUES" \
    --ubatch-size "$UBATCH_VALUES" \
    --device "$DEVICE" \
    --n-gpu-layers 999 \
    --cache-type-k f16 \
    --cache-type-v f16 \
    --flash-attn on \
    --mmap 0 \
    --repetitions "$REPETITIONS" \
    --output "$OUTPUT"