Frank
55f87fcdce
The 2026-10-09 wire aliases become the service names everywhere: systemd units, serve scripts, env files and FRANK_* variables, deploy-plan/deploy-remote service keys, container names, Prometheus job names + alert rules, Grafana dashboard queries, bats seams, runbook filenames, homepage/AGENTS lore, and historical prose. Rollback tags renamed in lockstep. Residue in the tree: zero. Retired frank-medium/small/npu names are history and stay. Known casualty: scripts/patches/*.patch context lines were rewritten; those retired-era vLLM-fork patches no longer apply byte-exact.
130 lines
4.2 KiB
Bash
Executable File
130 lines
4.2 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Decode throughput benchmark for frank-dragoon.
|
|
# Measures generation tok/s with 8K+ token prompts and 256 generated tokens.
|
|
set -euo pipefail
|
|
|
|
SERVE=/home/dank/GitPackages/ROCmFPX/build-qwen38/bin/llama-server
|
|
MODEL=/home/dank/models/kingjones-Qwen3.8-Flash-Next-ROCmFP4-STRIX/Qwen3.8-Flash-Next-Q4_0-ROCmFP4-STRIX.gguf
|
|
PROMPT_FILE=/tmp/bench-prompts/prompt_code.txt
|
|
PORT=7770
|
|
N_GEN=256
|
|
SERVER_DIR=/home/dank/GitPackages/ROCmFPX/build-qwen38/bin
|
|
ROCM_PATH=/opt/rocm
|
|
LIB_PATH="$SERVER_DIR:$ROCM_PATH/lib:$ROCM_PATH/lib/rocm_sysdeps/lib:$ROCM_PATH/lib/llvm/lib"
|
|
|
|
kill_all() {
|
|
pkill -9 -f llama-server 2>/dev/null || true
|
|
sleep 3
|
|
}
|
|
|
|
wait_ready() {
|
|
for i in $(seq 1 600); do
|
|
if curl -s http://127.0.0.1:$PORT/health 2>/dev/null | grep -q ok; then
|
|
return 0
|
|
fi
|
|
sleep 1
|
|
done
|
|
return 1
|
|
}
|
|
|
|
run_bench() {
|
|
local tb=$1
|
|
local logfile=/tmp/server_tb${tb}.log
|
|
|
|
kill_all
|
|
|
|
# Start server
|
|
env HSA_OVERRIDE_GFX_VERSION=11.5.1 HIP_VISIBLE_DEVICES=0 \
|
|
LD_LIBRARY_PATH="$LIB_PATH" ROCM_PATH="$ROCM_PATH" \
|
|
nohup $SERVE \
|
|
--model "$MODEL" --port $PORT --jinja \
|
|
--device ROCm0 --gpu-layers 999 --fit off \
|
|
--threads 16 --threads-batch $tb \
|
|
--parallel 2 --ctx-size 131072 \
|
|
--batch-size 4096 --ubatch-size 4096 \
|
|
--flash-attn on \
|
|
--cache-type-k f16 --cache-type-v f16 \
|
|
--cache-prompt --cache-idle-slots --metrics \
|
|
--temp 0.7 --top-p 0.8 --top-k 20 --min-p 0.0 \
|
|
--reasoning on --reasoning-format deepseek \
|
|
--reasoning-budget -1 > "$logfile" 2>&1 &
|
|
|
|
if ! wait_ready; then
|
|
echo "TB=$tb: FAILED (server not ready)"
|
|
return 1
|
|
fi
|
|
|
|
# Warmup (small request)
|
|
curl -s -m 60 http://127.0.0.1:$PORT/v1/chat/completions \
|
|
-H "Content-Type: application/json" \
|
|
-d '{"model":"frank-dragoon","messages":[{"role":"user","content":"Hi"}],"max_tokens":16,"stream":false}' > /dev/null 2>&1 || true
|
|
|
|
# Build 8K prompt
|
|
local prompt
|
|
prompt=$(python3 -c "
|
|
import json
|
|
with open('$PROMPT_FILE') as f: text=f.read()
|
|
words=text.split()[:8200]
|
|
print(json.dumps(' '.join(words)))
|
|
")
|
|
|
|
echo "TB=$tb: Starting benchmark..."
|
|
|
|
# Benchmark
|
|
local t0 t1 resp pt gt wall gtps
|
|
t0=$(date +%s%N)
|
|
resp=$(curl -s -m 600 http://127.0.0.1:$PORT/v1/chat/completions \
|
|
-H "Content-Type: application/json" \
|
|
-d "{\"model\":\"frank-dragoon\",\"messages\":[{\"role\":\"user\",\"content\":$prompt}],\"max_tokens\":$N_GEN,\"stream\":false}" 2>&1)
|
|
t1=$(date +%s%N)
|
|
|
|
if ! echo "$resp" | python3 -c "import sys,json; json.load(sys.stdin)" 2>/dev/null; then
|
|
echo "TB=$tb: FAILED (HTTP error: $(echo "$resp" | head -1))"
|
|
return 1
|
|
fi
|
|
|
|
pt=$(echo "$resp" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d['usage']['prompt_tokens'])")
|
|
gt=$(echo "$resp" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d['usage']['completion_tokens'])")
|
|
wall=$(python3 -c "print(round(($t1-$t0)/1000000000,1))")
|
|
gtps=$(python3 -c "print(round($N_GEN/($t1-$t0)*1000000000,2))")
|
|
|
|
echo "TB=$tb: pt=$pt gt=$gt wall=${wall}s gen=${gtps} tok/s"
|
|
|
|
# Extract prefill timing from server log
|
|
local prefill_time
|
|
prefill_time=$(grep -oP 'prompt eval time = \K[0-9.]+' "$logfile" | head -1 || echo "N/A")
|
|
if [ "$prefill_time" != "N/A" ]; then
|
|
echo "TB=$tb: prefill=$(python3 -c "print(round($N_GEN/($wall),2))") tok/s"
|
|
fi
|
|
|
|
kill_all
|
|
sleep 2
|
|
|
|
echo "$tb,$gt,$wall,$gtps,$pt" >> /tmp/bench_decode_results.csv
|
|
}
|
|
|
|
# Main
|
|
echo "=== Decode throughput benchmark ==="
|
|
echo "Prompt: ~8K tokens, Generation: $N_GEN tokens"
|
|
echo ""
|
|
|
|
# Clear results
|
|
echo "tb,gen_tokens,wall_s,gen_tps,prompt_tokens" > /tmp/bench_decode_results.csv
|
|
|
|
# Run benchmarks
|
|
for tb in 16 32; do
|
|
run_bench $tb
|
|
echo ""
|
|
done
|
|
|
|
# Summary
|
|
echo "=== SUMMARY ==="
|
|
echo "Prefill throughput (from earlier benchmark):"
|
|
echo " TB=16: 373.5 tok/s"
|
|
echo " TB=32: 354.4 tok/s"
|
|
echo ""
|
|
echo "Decode throughput (generation tok/s with 8K prompt):"
|
|
tail -n +2 /tmp/bench_decode_results.csv | while IFS=, read tb gt wall gtps pt; do
|
|
echo " TB=$tb: $gt tokens in ${wall}s = ${gtps} tok/s (pt=$pt)"
|
|
done
|