fix(bench): newer cortiq pretty-prints --json — parse it, and report honest tok/s

The one-click model benchmark showed "error" even though cortiq bench ran
fine: the parser expected the JSON result on a single line, while newer
cortiq releases pretty-print it across many. Extraction now finds the last
balanced JSON object anywhere in the mixed CLI output (both formats work).

Also hardened tok/s selection: steady decode speed (decode_tok_s_steady)
is preferred over incl-prefill, and the loose "contains tok+per" fallback —
which would happily report allocs_per_token=769 as tok/s — now only matches
*tok_s* / *tokens_per* fields.
This commit is contained in:
infosave2007
2026-08-07 19:32:47 +03:00
parent 1bba427042
commit 9af51b679e
+71 -12
View File
@@ -32,11 +32,19 @@ fn now() -> u64 {
.as_secs()
}
/// tok/s out of the benchmark's JSON: first numeric field whose key mentions
/// tokens-per-second (the exact name has varied across cortiq releases).
/// tok/s out of the benchmark's JSON: known field names first (steady decode
/// speed is the honest number), then any `*tok_s*` field as a fallback. The
/// old loose "contains tok + per" heuristic could grab `allocs_per_token`.
fn extract_tok_s(v: &serde_json::Value) -> Option<f64> {
let obj = v.as_object()?;
for want in ["tok_s", "tok_per_s", "tokens_per_sec", "decode_tok_s"] {
for want in [
"decode_tok_s_steady",
"decode_tok_s_incl_prefill",
"decode_tok_s",
"tok_s",
"tok_per_s",
"tokens_per_sec",
] {
if let Some(n) = obj.get(want).and_then(|x| x.as_f64()) {
return Some(n);
}
@@ -44,12 +52,44 @@ fn extract_tok_s(v: &serde_json::Value) -> Option<f64> {
obj.iter()
.find(|(k, val)| {
let k = k.to_ascii_lowercase();
(k.contains("tok") && (k.contains("/s") || k.contains("_s") || k.contains("per")))
&& val.as_f64().is_some()
(k.contains("tok_s") || k.contains("tokens_per")) && val.as_f64().is_some()
})
.and_then(|(_, val)| val.as_f64())
}
/// Last parseable JSON object in mixed CLI output. Newer cortiq releases
/// pretty-print the `--json` result over many lines, older ones emit a single
/// line — this handles both, skipping any log noise around it.
fn last_json_object(text: &str) -> Option<serde_json::Value> {
let mut end = text.len();
while let Some(close) = text[..end].rfind('}') {
let mut depth = 0i32;
let mut start = None;
for (i, c) in text[..=close].char_indices().rev() {
match c {
'}' => depth += 1,
'{' => {
depth -= 1;
if depth == 0 {
start = Some(i);
break;
}
}
_ => {}
}
}
if let Some(st) = start {
if let Ok(v) = serde_json::from_str::<serde_json::Value>(&text[st..=close]) {
if v.is_object() {
return Some(v);
}
}
}
end = close;
}
None
}
impl BenchStore {
pub fn new() -> Arc<Self> {
Arc::new(Self::default())
@@ -125,13 +165,7 @@ pub fn start(
if n > 30 {
run.log.drain(0..n - 30);
}
// the --json contract: one JSON object on its own line
let parsed = text
.lines()
.rev()
.map(str::trim)
.find(|l| l.starts_with('{') && l.ends_with('}'))
.and_then(|l| serde_json::from_str::<serde_json::Value>(l).ok());
let parsed = last_json_object(&text);
match parsed {
Some(v) if o.status.success() => {
run.tok_s = extract_tok_s(&v);
@@ -163,4 +197,29 @@ mod tests {
let v = serde_json::json!({"decode_tokens_per_sec": 31.0});
assert_eq!(extract_tok_s(&v), Some(31.0));
}
#[test]
fn steady_decode_wins_and_allocs_never_matches() {
let v = serde_json::json!({
"allocs_per_token": 769.4,
"decode_tok_s_incl_prefill": 9.98,
"decode_tok_s_steady": 11.86,
"prefill_tok_s": 25.5,
});
assert_eq!(extract_tok_s(&v), Some(11.86));
let v = serde_json::json!({"allocs_per_token": 769.4, "seq_len": 140});
assert_eq!(extract_tok_s(&v), None);
}
#[test]
fn json_found_single_line_and_pretty() {
let single = "noise\n{\"tok_s\": 5.0}\nmore noise";
assert_eq!(last_json_object(single).unwrap()["tok_s"], 5.0);
let pretty = "INFO loading\n{\n \"decode_tok_s_steady\": 11.86,\n \"seq_len\": 140\n}\nINFO done {not json";
assert_eq!(
last_json_object(pretty).unwrap()["decode_tok_s_steady"],
11.86
);
assert!(last_json_object("no braces here").is_none());
}
}