zhoulin
26b071c6e1
- _cudagraph_plugin: warm up autotune/JIT explicitly before graph capture (internal 5-iter warmup is too short), tag fallback markers with the failing phase; first-run latency no longer jitters run-to-run. - _device_guard_plugin (new): set GEMS_VENDOR via torch probe before importing flag_gems, avoiding its timeout-less nvidia-smi subprocess probe that can hang import in fork-broken environments. - _pretty_report_plugin (new) + _term_style (new): fold inputs identical across all result rows into a legend line, color status/plugin tags/markers on the live terminal; run.log is ANSI-stripped and keeps upstream SUCCESS/column wording for grep compatibility. - run_pytest.sh: make USE_FLAGTUNE overridable, group all knobs into a config section with Chinese comments, add start/end banners. - README: document the warmup semantics, new plugins/env vars, and the A/B rule that both sides must use the same USE_FLAGTUNE.
43 lines
1.3 KiB
Python
43 lines
1.3 KiB
Python
"""pytest plugin: seed random/numpy/torch RNG for reproducible benchmark inputs.
|
|
|
|
Data-dependent kernels (sort, topk, nonzero, ...) have value-dependent latency;
|
|
a fixed seed makes every run generate byte-identical inputs, so the latency
|
|
delta between two runs reflects the change under test, not the input data.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
|
|
_SEED = 0
|
|
|
|
|
|
def pytest_configure(config):
|
|
seed = _SEED
|
|
# random.seed too: some kits (cutlass_scaled_mm) pick cases via random.shuffle.
|
|
import random
|
|
random.seed(seed)
|
|
seeded = ["random"]
|
|
try:
|
|
import numpy as _np
|
|
_np.random.seed(seed)
|
|
seeded.append("numpy")
|
|
except Exception:
|
|
pass
|
|
try:
|
|
import torch
|
|
except Exception as exc: # torch missing should never happen here, stay safe
|
|
from _term_style import tag
|
|
print(f"{tag('[seed-plugin]')} torch unavailable, "
|
|
f"seeded {'+'.join(seeded)} only: {exc}",
|
|
file=sys.stderr)
|
|
return
|
|
torch.manual_seed(seed)
|
|
if torch.cuda.is_available():
|
|
torch.cuda.manual_seed_all(seed)
|
|
seeded.append("torch")
|
|
from _term_style import tag
|
|
print(f"{tag('[seed-plugin]')} manual_seed({seed}) for {'+'.join(seeded)} "
|
|
"— reproducible benchmark inputs/cases",
|
|
file=sys.stderr, flush=True)
|