Files
wehub-resource-sync 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
chore: import upstream snapshot with attribution
2026-07-13 12:38:16 +08:00

112 lines
3.9 KiB
Python

import time
from concurrent.futures import ThreadPoolExecutor, as_completed
import requests
_REQUEST_TIMEOUT = 180
class PauseResumeInPlaceMixin:
"""Test pause/resume with in_place mode.
Sends concurrent requests, pauses mid-generation, verifies no progress
during the pause window, then resumes and verifies all requests complete.
Subclass must set:
- pause_generate_url: URL to send /generate requests (or falls back to self.base_url)
- pause_target_urls: list of URLs to send /pause_generation and /continue_generation
"""
pause_num_requests: int = 32
pause_max_new_tokens: int = 512
pause_duration: float = 5
pause_generate_url: str = ""
pause_target_urls: list = []
def test_pause_resume_in_place(self):
generate_url = self.pause_generate_url or self.base_url
target_urls = self.pause_target_urls or [self.base_url]
num_requests = self.pause_num_requests
def _generate(prompt_id):
return requests.post(
generate_url + "/generate",
json={
"text": f"Question {prompt_id}: Write a short essay about the number {prompt_id}.",
"sampling_params": {
"temperature": 0.8,
"max_new_tokens": self.pause_max_new_tokens,
},
},
timeout=_REQUEST_TIMEOUT,
)
with ThreadPoolExecutor(max_workers=num_requests) as executor:
futures = {executor.submit(_generate, i): i for i in range(num_requests)}
time.sleep(1)
# Pause all targets
for url in target_urls:
requests.post(
url + "/pause_generation",
json={"mode": "in_place"},
timeout=30,
).raise_for_status()
time.sleep(0.5)
done_before = sum(1 for f in futures if f.done())
time.sleep(self.pause_duration)
done_after = sum(1 for f in futures if f.done())
self.assertLess(
done_before,
num_requests,
"All requests completed before pause took effect -- "
"increase pause_max_new_tokens to make the test meaningful.",
)
self.assertEqual(
done_after - done_before,
0,
f"{done_after - done_before} requests completed during pause "
f"({done_before} before, {done_after} after) -- "
f"pause_generation was not respected by the scheduler.",
)
# Resume all targets (reverse order to unblock downstream first)
for url in reversed(target_urls):
requests.post(
url + "/continue_generation",
json={},
timeout=30,
).raise_for_status()
completed = 0
errors = []
for future in as_completed(futures, timeout=_REQUEST_TIMEOUT):
prompt_id = futures[future]
try:
resp = future.result()
if resp.status_code == 200:
body = resp.json()
self.assertIn("text", body)
self.assertGreater(len(body["text"]), 0)
completed += 1
else:
errors.append(f"Request {prompt_id}: status={resp.status_code}")
except Exception as e:
errors.append(f"Request {prompt_id}: exception={e}")
self.assertEqual(
completed + len(errors),
num_requests,
"Some requests did not resolve within the timeout -- likely hung during pause.",
)
self.assertEqual(
completed,
num_requests,
f"Some requests failed: {completed}/{num_requests} succeeded. Errors: {errors}",
)