94057c3d3e
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
CI Model Inventory / build-inventory (push) Has been cancelled
Lint / lint (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Summary (push) Has been cancelled
PR Test (SMG) / build-wheel (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Has been cancelled
PR Test (SMG) / python-unit-tests (push) Has been cancelled
PR Test (SMG) / unit-tests (push) Has been cancelled
PR Test (SMG) / benchmarks (push) Has been cancelled
PR Test (SMG) / chat-completions (push) Has been cancelled
PR Test (SMG) / chat-completions-4gpu (push) Has been cancelled
PR Test (SMG) / e2e (push) Has been cancelled
PR Test (SMG) / docker-build-test (push) Has been cancelled
PR Test (SMG) / k8s-integration (push) Has been cancelled
PR Test (SMG) / finish (push) Has been cancelled
PR Test (SMG) / summarize-benchmarks (push) Has been cancelled
Release SGLang Model Gateway Docker Image / publish (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Build SDist (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu129 (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu130 (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Has been cancelled
Release SGLang Kernels / release-rocm700 (push) Has been cancelled
Release SGLang Kernels / release-rocm720 (push) Has been cancelled
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Has been cancelled
Release SGLang Kernels / release-musa43 (push) Has been cancelled
146 lines
4.7 KiB
Python
146 lines
4.7 KiB
Python
from __future__ import annotations
|
|
|
|
import time
|
|
from typing import Literal, Optional
|
|
|
|
from sglang.srt.kv_canary.perturb.config import TargetGroupKind
|
|
from sglang.test.kv_canary.violation_log_utils import (
|
|
assert_no_violation_in_log,
|
|
find_violation_in_log,
|
|
)
|
|
|
|
_Side = Optional[Literal["prefill", "decode"]]
|
|
|
|
|
|
class CanaryViolationAssertMixin:
|
|
def _captured_log_text(self, side: _Side = None) -> str:
|
|
raise NotImplementedError
|
|
|
|
def assert_per_forward_violation_reported(
|
|
self,
|
|
*,
|
|
fail_reason: str,
|
|
target_group: Optional[TargetGroupKind] = None,
|
|
side: _Side = None,
|
|
flush_wait_seconds: float = 2.0,
|
|
) -> None:
|
|
suffix = "" if target_group is None else f"_{target_group.name}"
|
|
self.assert_violation_logged_any(
|
|
launch_tag_patterns=(f"HEAD_*{suffix}", f"TAIL_*{suffix}"),
|
|
fail_reason=fail_reason,
|
|
side=side,
|
|
flush_wait_seconds=flush_wait_seconds,
|
|
)
|
|
|
|
def assert_sweep_violation_reported(
|
|
self,
|
|
*,
|
|
fail_reason: str,
|
|
target_group: TargetGroupKind,
|
|
side: _Side = None,
|
|
flush_wait_seconds: float = 2.0,
|
|
max_retries: int = 4,
|
|
) -> None:
|
|
self.assert_violation_logged_any(
|
|
launch_tag_patterns=(f"SWEEP_*_{target_group.name}",),
|
|
fail_reason=fail_reason,
|
|
side=side,
|
|
flush_wait_seconds=flush_wait_seconds,
|
|
max_retries=max_retries,
|
|
)
|
|
|
|
def assert_any_launch_tag_violation_reported(
|
|
self,
|
|
*,
|
|
fail_reason: str,
|
|
side: _Side = None,
|
|
flush_wait_seconds: float = 3.0,
|
|
max_retries: int = 10,
|
|
) -> None:
|
|
self.assert_violation_logged_any(
|
|
launch_tag_patterns=("*",),
|
|
fail_reason=fail_reason,
|
|
side=side,
|
|
flush_wait_seconds=flush_wait_seconds,
|
|
max_retries=max_retries,
|
|
)
|
|
|
|
def assert_any_launch_tag_violation_absent(
|
|
self, *, fail_reason: str, side: _Side = None
|
|
) -> None:
|
|
self.assert_no_violation_matching(
|
|
launch_tag_patterns=("*",), fail_reason=fail_reason, side=side
|
|
)
|
|
|
|
def assert_violation_logged_any(
|
|
self,
|
|
*,
|
|
launch_tag_patterns: tuple[str, ...],
|
|
fail_reason: str,
|
|
side: _Side = None,
|
|
flush_wait_seconds: float = 2.0,
|
|
max_retries: int = 1,
|
|
) -> None:
|
|
log_text = ""
|
|
for _ in range(max_retries):
|
|
time.sleep(flush_wait_seconds)
|
|
log_text = self._captured_log_text(side)
|
|
if find_violation_in_log(
|
|
log_text,
|
|
launch_tag_patterns=launch_tag_patterns,
|
|
fail_reason=fail_reason,
|
|
):
|
|
return
|
|
side_label = "" if side is None else f" on side={side}"
|
|
other_side_diag = ""
|
|
if side in ("prefill", "decode"):
|
|
other = "decode" if side == "prefill" else "prefill"
|
|
try:
|
|
other_text = self._captured_log_text(other)
|
|
other_match = find_violation_in_log(
|
|
other_text,
|
|
launch_tag_patterns=launch_tag_patterns,
|
|
fail_reason=fail_reason,
|
|
)
|
|
other_side_diag = (
|
|
f"\n[diag] other side ({other}) buf len={len(other_text)} "
|
|
f"contains_match={other_match}"
|
|
)
|
|
except (NotImplementedError, ValueError):
|
|
pass
|
|
raise AssertionError(
|
|
f"No canary violation matching launch_tag_patterns={launch_tag_patterns!r} "
|
|
f"fail_reason={fail_reason!r}{side_label} after max_retries={max_retries} "
|
|
f"(wait={flush_wait_seconds}s each). "
|
|
f"log_text len={len(log_text)}.{other_side_diag} Log tail:\n"
|
|
f"{log_text[-2000:]}"
|
|
)
|
|
|
|
def assert_no_violation_matching(
|
|
self,
|
|
*,
|
|
launch_tag_patterns: tuple[str, ...],
|
|
fail_reason: str,
|
|
side: _Side = None,
|
|
) -> None:
|
|
log_text = self._captured_log_text(side)
|
|
if find_violation_in_log(
|
|
log_text,
|
|
launch_tag_patterns=launch_tag_patterns,
|
|
fail_reason=fail_reason,
|
|
):
|
|
raise AssertionError(
|
|
f"Unexpected canary violation matching "
|
|
f"launch_tag_patterns={launch_tag_patterns!r} "
|
|
f"fail_reason={fail_reason!r}. Log tail:\n{log_text[-2000:]}"
|
|
)
|
|
|
|
def assert_no_violation(
|
|
self,
|
|
*,
|
|
side: _Side = None,
|
|
wait_seconds: float = 2.0,
|
|
) -> None:
|
|
time.sleep(wait_seconds)
|
|
assert_no_violation_in_log(self._captured_log_text(side))
|