url/colibri
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #276 from KingIcyCreamProjects/pr/bench-parser-fix

Browse Source 
benchmark_cuda_fixture: accept the current PROFILE service/wait format
This commit is contained in:
Vincenzo
2026-07-16 07:51:37 +02:00
committed by GitHub
parent 1a8371631b 51dd4805af
commit 965e8a80aa
1 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
c/tools/benchmark_cuda_fixture.py
+6 -2
View File
@@ -10,8 +10,10 @@ from pathlib import Path
SPEED_RE = re.compile(r"REPLAY decode:.*\| ([0-9.]+) tok/s") SPEED_RE = re.compile(r"REPLAY decode:.*\| ([0-9.]+) tok/s")
# accetta sia il formato storico "expert-disk 0.123s |" sia quello attuale
# "expert-disk 0.123s service / 0.045s wait |" (glm.c profile_print)
PROFILE_RE = re.compile( PROFILE_RE = re.compile(
r"PROFILE: expert-disk ([0-9.]+)s \| expert-matmul ([0-9.]+)s " r"PROFILE: expert-disk ([0-9.]+)s(?: service / ([0-9.]+)s wait)? \| expert-matmul ([0-9.]+)s "
r"\| attention ([0-9.]+)s .* lm_head ([0-9.]+)s \| other ([0-9.-]+)s" r"\| attention ([0-9.]+)s .* lm_head ([0-9.]+)s \| other ([0-9.-]+)s"
) )
PROFILE_KEYS = ("disk", "expert_matmul", "attention", "lm_head", "other") PROFILE_KEYS = ("disk", "expert_matmul", "attention", "lm_head", "other")
@@ -23,7 +25,9 @@ def parse_output(stdout: str, stderr: str = "") -> tuple[float, list[float]]:
profile = PROFILE_RE.search(stdout) profile = PROFILE_RE.search(stdout)
if not speed or not profile: if not speed or not profile:
raise RuntimeError(f"benchmark output missing\nstdout:\n{stdout}\nstderr:\n{stderr}") raise RuntimeError(f"benchmark output missing\nstdout:\n{stdout}\nstderr:\n{stderr}")
return float(speed.group(1)), [float(value) for value in profile.groups()] service, wait, *rest = profile.groups()
disk = float(service) + (float(wait) if wait else 0.0)
return float(speed.group(1)), [disk] + [float(value) for value in rest]
def execute(engine: str, env: dict[str, str]) -> tuple[float, list[float]]: def execute(engine: str, env: dict[str, str]) -> tuple[float, list[float]]: