From 0766ef39496981fc27be0f2671b02e4e1814c530 Mon Sep 17 00:00:00 2001
From: yujung7768903 <yu-jung31476@naver.com>
Date: Mon, 14 Sep 2026 23:59:41 +0900
Subject: [PATCH] fix(bench): make run_bench.sh portable and stop hardcoding
 the run date

run_bench.sh recorded a fixed `DATE="2026-03-15"` in every CSV row, so
benchmark results were stamped with a date unrelated to the run.

It also parsed tok/s with `grep -oP`, which is GNU-only. BSD grep (macOS)
rejects `-P`, so both tok/s fields came back empty and every run was written
as a FAILED row even when the benchmark succeeded.

- DATE is now `date +%F`
- HARDWARE and MLX_VERSION are environment-overridable, defaults unchanged
- tok/s and ms parsing moved to `sed -n -E`, which works under BSD and GNU sed
- added `set -euo pipefail` plus an argument check; the parse helpers are
  written so a failed run still falls through to the existing FAILED row

resolves #1666

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
---
 benchmarks/run_bench.sh | 35 ++++++++++++++++++++++++-----------
 1 file changed, 24 insertions(+), 11 deletions(-)

diff --git a/benchmarks/run_bench.sh b/benchmarks/run_bench.sh
index 87820f4ad..aeba23983 100755
--- a/benchmarks/run_bench.sh
+++ b/benchmarks/run_bench.sh
@@ -1,29 +1,42 @@
 #!/bin/bash
 # Single-model benchmark runner
 # Usage: ./run_bench.sh <model_path> <csv_file>
+set -euo pipefail
+
+if [ $# -lt 2 ]; then
+    echo "Usage: $0 <model_path> <csv_file>" >&2
+    exit 1
+fi
 
 MODEL_PATH="$1"
 CSV_FILE="$2"
 MODEL_NAME=$(basename "$MODEL_PATH")
 PROMPT="Explain the concept of machine learning in simple terms."
 MAX_TOKENS=100
-DATE="2026-03-15"
-HARDWARE="NVIDIA_GB10_CUDA13.0"
-MLX_VERSION="0.31.1"
+DATE=$(date +%F)
+HARDWARE="${HARDWARE:-NVIDIA_GB10_CUDA13.0}"
+MLX_VERSION="${MLX_VERSION:-0.31.1}"
 BUILD_TYPE="release"
 BINARY="./target/release/mlxcel"
 
 echo ">>> Benchmarking: $MODEL_NAME"
 
-OUTPUT=$($BINARY generate -m "$MODEL_PATH" -p "$PROMPT" -n $MAX_TOKENS --profile 2>&1)
+# A failed run is a row too -- let it reach the FAILED branch instead of
+# aborting under `set -e`.
+OUTPUT=$($BINARY generate -m "$MODEL_PATH" -p "$PROMPT" -n $MAX_TOKENS --profile 2>&1) || true
+
+# Parse results. `sed -n ...p` rather than grep: a run that produced no stats
+# must still reach the FAILED row below, and grep's no-match exit 1 would
+# abort it under `set -e`.
+field() { printf '%s\n' "$OUTPUT" | sed -n -E "s/^[[:space:]]*$1:[[:space:]]*([0-9.]+).*/\1/p"; }
+tok_per_sec() { printf '%s\n' "$OUTPUT" | sed -n -E "s/^[[:space:]]*$1:.*\(([0-9.]+) tok\/s\).*/\1/p"; }
 
-# Parse results
-PROMPT_TOKENS=$(echo "$OUTPUT" | grep "Prompt tokens:" | sed 's/.*: *//')
-GEN_TOKENS=$(echo "$OUTPUT" | grep "Generated tokens:" | sed 's/.*: *//')
-PREFILL_MS=$(echo "$OUTPUT" | grep "Prefill:" | sed 's/.*: *//' | sed 's/ ms.*//')
-PREFILL_TOKS=$(echo "$OUTPUT" | grep "Prefill:" | grep -oP '[\d.]+(?= tok/s)')
-DECODE_MS=$(echo "$OUTPUT" | grep "Decode:" | sed 's/.*: *//' | sed 's/ ms.*//')
-DECODE_TOKS=$(echo "$OUTPUT" | grep "Decode:" | grep -oP '[\d.]+(?= tok/s)')
+PROMPT_TOKENS=$(field "Prompt tokens")
+GEN_TOKENS=$(field "Generated tokens")
+PREFILL_MS=$(field "Prefill")
+PREFILL_TOKS=$(tok_per_sec "Prefill")
+DECODE_MS=$(field "Decode")
+DECODE_TOKS=$(tok_per_sec "Decode")
 
 if [ -z "$DECODE_TOKS" ]; then
     echo "    FAILED or no output"