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
61 lines
2.2 KiB
Python
61 lines
2.2 KiB
Python
"""Parent-death watchdog for MLX workers on Apple Silicon.
|
|
|
|
macOS has no ``PR_SET_PDEATHSIG`` equivalent, so the kernel will not signal a
|
|
worker process when its parent dies; the worker would be reparented to PID 1
|
|
and leak (holding GPU/host memory and ports). This module emulates PDEATHSIG
|
|
with a daemon thread that watches the parent PID via kqueue and SIGKILLs the
|
|
current process once it gets orphaned.
|
|
"""
|
|
|
|
import os
|
|
import select
|
|
import signal
|
|
import threading
|
|
|
|
|
|
def start_parent_death_watcher() -> None:
|
|
"""SIGKILL this process once its current parent exits (macOS only).
|
|
|
|
kqueue with an ``EVFILT_PROC`` / ``NOTE_EXIT`` filter is the native,
|
|
event-driven mechanism on macOS (exposed via ``select.kqueue`` /
|
|
``select.kevent``), so the watcher thread blocks until the parent actually
|
|
exits instead of waking up to poll.
|
|
|
|
``SIGKILL`` is sent from this watcher thread and is uncatchable /
|
|
unblockable, so it works even when the main thread is stuck inside a
|
|
blocking native call (e.g. an MLX/Metal ``mx.eval`` / ``.tolist()``).
|
|
"""
|
|
original_ppid = os.getppid()
|
|
|
|
def _watch_parent():
|
|
kq = select.kqueue()
|
|
kev = select.kevent(
|
|
original_ppid,
|
|
filter=select.KQ_FILTER_PROC,
|
|
flags=select.KQ_EV_ADD,
|
|
fflags=select.KQ_NOTE_EXIT,
|
|
)
|
|
try:
|
|
# Register the EVFILT_PROC / NOTE_EXIT watch on the parent PID.
|
|
kq.control([kev], 0, None)
|
|
except (ProcessLookupError, OSError):
|
|
# The parent already exited before we could register the watch
|
|
# (ESRCH); we are already orphaned.
|
|
os.kill(os.getpid(), signal.SIGKILL)
|
|
return
|
|
# Guard against the race where the parent exits between reading
|
|
# original_ppid and registering the watch above.
|
|
if os.getppid() != original_ppid:
|
|
os.kill(os.getpid(), signal.SIGKILL)
|
|
return
|
|
# Block until the parent exits, then terminate ourselves.
|
|
kq.control(None, 1, None)
|
|
os.kill(os.getpid(), signal.SIGKILL)
|
|
|
|
watcher = threading.Thread(
|
|
target=_watch_parent,
|
|
name="parent-death-watcher",
|
|
daemon=True,
|
|
)
|
|
watcher.start()
|