Support unifying axis ordering in dump comparator (#19456)

This commit is contained in:
fzyzcjy
2026-02-27 08:08:32 +08:00
committed by GitHub
parent 425d333ee3
commit 8ac64e1487
6 changed files with 230 additions and 0 deletions
@@ -0,0 +1,74 @@
import sys
from typing import Optional
import pytest
import torch
from sglang.srt.debug_utils.comparator.aligner.axis_swapper import (
AxisSwapperPlan,
compute_axis_swapper_plan,
execute_axis_swapper_plan,
)
from sglang.srt.debug_utils.comparator.utils import Pair
from sglang.srt.debug_utils.comparator.warning_sink import warning_sink
from sglang.test.ci.ci_register import register_cpu_ci
register_cpu_ci(est_time=15, suite="default", nightly=True)
class TestComputeAxisSwapperPlan:
def test_no_dims_returns_none(self) -> None:
assert compute_axis_swapper_plan(Pair(x=None, y=None)) is None
assert compute_axis_swapper_plan(Pair(x="t h d", y=None)) is None
assert compute_axis_swapper_plan(Pair(x=None, y="t h d")) is None
def test_same_order_returns_none(self) -> None:
result: Optional[AxisSwapperPlan] = compute_axis_swapper_plan(
Pair(x="t h d", y="t h d")
)
assert result is None
def test_different_order(self) -> None:
result: Optional[AxisSwapperPlan] = compute_axis_swapper_plan(
Pair(x="t h d", y="t d h")
)
assert result is not None
assert result.pattern == "t h d -> t d h"
def test_name_mismatch_returns_none_with_warning(self) -> None:
with warning_sink.context() as warnings:
result: Optional[AxisSwapperPlan] = compute_axis_swapper_plan(
Pair(x="t h d", y="t h e")
)
assert result is None
assert len(warnings) == 1
assert warnings[0].category == "axis_swapper_dim_mismatch"
assert "dim name sets differ" in warnings[0].message
def test_modifiers_ignored_for_name_extraction(self) -> None:
result: Optional[AxisSwapperPlan] = compute_axis_swapper_plan(
Pair(x="t h(tp) d", y="t d h(tp)")
)
assert result is not None
assert result.pattern == "t h d -> t d h"
class TestExecuteAxisSwapperPlan:
def test_rearrange(self) -> None:
torch.manual_seed(42)
tensor: torch.Tensor = torch.randn(4, 8, 16)
plan = AxisSwapperPlan(pattern="t h d -> t d h")
result: torch.Tensor = execute_axis_swapper_plan(tensor=tensor, plan=plan)
assert result.shape == (4, 16, 8)
for i in range(4):
assert torch.equal(
result[i],
tensor[i].T,
)
if __name__ == "__main__":
sys.exit(pytest.main([__file__]))
@@ -882,6 +882,80 @@ class TestEntrypointGroupingLogical:
assert comp.name == "hidden"
class TestEntrypointAxisSwapper:
"""Test cross-framework dim reordering through the full entrypoint pipeline."""
def test_axis_swap_different_dim_order(self, tmp_path, capsys):
"""Baseline dims 'b h d' vs target dims 'b d h': axis swapper rearranges baseline to match."""
torch.manual_seed(42)
full_tensor = torch.randn(4, 8, 16)
baseline_dir = tmp_path / "baseline"
target_dir = tmp_path / "target"
_create_rank_dump(
baseline_dir,
rank=0,
name="hidden",
tensor=full_tensor,
dims="b h d",
)
_create_rank_dump(
target_dir,
rank=0,
name="hidden",
tensor=full_tensor.permute(0, 2, 1).contiguous(),
dims="b d h",
)
args = _make_args(
baseline_dir / _FIXED_EXP_NAME,
target_dir / _FIXED_EXP_NAME,
diff_threshold=1e-3,
)
records = _run_and_parse(args, capsys)
comp = _assert_single_comparison_passed(records)
assert comp.name == "hidden"
assert comp.baseline.shape == [4, 16, 8]
assert comp.target.shape == [4, 16, 8]
def test_axis_swap_with_tp_unshard(self, tmp_path, capsys):
"""Baseline TP=2 with dims 'b h(tp) d' vs target TP=2 with dims 'b d h(tp)': unshard + axis swap."""
torch.manual_seed(42)
full_tensor = torch.randn(4, 8, 16)
baseline_dir = tmp_path / "baseline"
target_dir = tmp_path / "target"
_create_tp_sharded_dumps(
baseline_dir,
full_tensor=full_tensor,
name="hidden",
tp_size=2,
shard_dim=1,
dims_str="b h(tp) d",
)
_create_tp_sharded_dumps(
target_dir,
full_tensor=full_tensor.permute(0, 2, 1).contiguous(),
name="hidden",
tp_size=2,
shard_dim=2,
dims_str="b d h(tp)",
)
args = _make_args(
baseline_dir / _FIXED_EXP_NAME,
target_dir / _FIXED_EXP_NAME,
diff_threshold=1e-3,
)
records = _run_and_parse(args, capsys)
comp = _assert_single_comparison_passed(records)
assert comp.name == "hidden"
class TestEntrypointReplicatedAxis:
"""Test replicated-axis scenarios through the full entrypoint pipeline."""