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
82 lines
2.4 KiB
Python
82 lines
2.4 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
import tempfile
|
|
from pathlib import Path
|
|
|
|
import numpy as np
|
|
import pytest
|
|
|
|
from sglang.multimodal_gen.runtime import ipc_array
|
|
from sglang.multimodal_gen.runtime.ipc_array import (
|
|
NumpyArrayFileRef,
|
|
is_local_endpoint,
|
|
materialize_file_refs,
|
|
spill_large_arrays_to_file_refs,
|
|
)
|
|
|
|
|
|
def test_spill_large_arrays_round_trips_and_removes_file(monkeypatch, tmp_path):
|
|
monkeypatch.setattr(ipc_array, "_array_ipc_dir", lambda: str(tmp_path))
|
|
array = np.arange(ipc_array._MIN_FILE_REF_BYTES, dtype=np.uint8)
|
|
|
|
spilled = spill_large_arrays_to_file_refs([array])
|
|
|
|
assert isinstance(spilled[0], NumpyArrayFileRef)
|
|
spilled_path = Path(spilled[0].path)
|
|
assert spilled_path.exists()
|
|
|
|
materialized = materialize_file_refs(spilled)
|
|
|
|
assert np.array_equal(materialized[0], array)
|
|
assert not spilled_path.exists()
|
|
|
|
|
|
def test_small_arrays_are_kept_inline():
|
|
array = np.arange(16, dtype=np.uint8)
|
|
|
|
spilled = spill_large_arrays_to_file_refs((array,))
|
|
|
|
assert spilled[0] is array
|
|
|
|
|
|
def test_large_arrays_are_kept_inline_without_shm(monkeypatch):
|
|
monkeypatch.setattr(ipc_array, "_array_ipc_dir", lambda: None)
|
|
array = np.arange(ipc_array._MIN_FILE_REF_BYTES, dtype=np.uint8)
|
|
|
|
spilled = spill_large_arrays_to_file_refs(array)
|
|
|
|
assert spilled is array
|
|
|
|
|
|
def test_spill_removes_temp_file_when_save_fails(monkeypatch, tmp_path):
|
|
monkeypatch.setattr(ipc_array, "_array_ipc_dir", lambda: str(tmp_path))
|
|
array = np.arange(ipc_array._MIN_FILE_REF_BYTES, dtype=np.uint8)
|
|
created_paths = []
|
|
|
|
def fail_save(*args, **kwargs):
|
|
raise OSError("simulated write failure")
|
|
|
|
original_mkstemp = tempfile.mkstemp
|
|
|
|
def tracked_mkstemp(*args, **kwargs):
|
|
fd, path = original_mkstemp(*args, **kwargs)
|
|
created_paths.append(Path(path))
|
|
return fd, path
|
|
|
|
monkeypatch.setattr(tempfile, "mkstemp", tracked_mkstemp)
|
|
monkeypatch.setattr(np, "save", fail_save)
|
|
|
|
with pytest.raises(OSError, match="simulated write failure"):
|
|
spill_large_arrays_to_file_refs(array)
|
|
|
|
assert created_paths
|
|
assert not created_paths[0].exists()
|
|
|
|
|
|
def test_local_endpoint_detection():
|
|
assert is_local_endpoint("tcp://127.0.0.1:30000")
|
|
assert is_local_endpoint("tcp://localhost:30000")
|
|
assert is_local_endpoint("ipc:///tmp/sgl.sock")
|
|
assert is_local_endpoint("inproc://scheduler")
|
|
assert not is_local_endpoint("tcp://10.0.0.2:30000")
|