sgl-project--sglang
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
84 行
2.3 KiB
Python
84 行
2.3 KiB
Python
"""Per-commit streaming-session tests.
|
|
|
|
Default config + EagleV2RetractLargePage + abort-leak repro stay per-commit.
|
|
Other variants (Retract / Eagle / EagleV2 / EagleRetractLargePage) live in
|
|
test_streaming_session_extra.py.
|
|
"""
|
|
|
|
import unittest
|
|
|
|
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
|
|
from sglang.test.kits.streaming_session_kit import (
|
|
AbortLeakReproKitMixin,
|
|
StreamingSessionKitMixin,
|
|
)
|
|
from sglang.test.server_fixtures.streaming_session_fixture import (
|
|
ABORT_REPRO_CHUNKED_PREFILL_SIZE,
|
|
ABORT_REPRO_CONTEXT_LEN,
|
|
ABORT_REPRO_PAGE_SIZE,
|
|
StreamingSessionServerBase,
|
|
)
|
|
from sglang.test.test_utils import (
|
|
DEFAULT_DRAFT_MODEL_EAGLE3,
|
|
DEFAULT_TARGET_MODEL_EAGLE3,
|
|
)
|
|
|
|
register_cuda_ci(est_time=691, stage="base-b", runner_config="1-gpu-large")
|
|
register_amd_ci(est_time=691, suite="stage-b-test-1-gpu-large-amd")
|
|
|
|
|
|
class TestStreamingSession(StreamingSessionServerBase, StreamingSessionKitMixin):
|
|
"""Default streaming-session config (small model, no spec)."""
|
|
|
|
extra_args = ["--chunked-prefill-size", "512"]
|
|
|
|
|
|
class TestStreamingSessionEagleV2RetractLargePage(TestStreamingSession):
|
|
"""EAGLE3 spec v2 + retract + page=256."""
|
|
|
|
model = DEFAULT_TARGET_MODEL_EAGLE3
|
|
extra_args = [
|
|
"--chunked-prefill-size",
|
|
"4096",
|
|
"--dtype=float16",
|
|
"--speculative-algorithm",
|
|
"EAGLE3",
|
|
"--speculative-draft-model",
|
|
DEFAULT_DRAFT_MODEL_EAGLE3,
|
|
"--speculative-num-steps",
|
|
"3",
|
|
"--speculative-eagle-topk",
|
|
"1",
|
|
"--speculative-num-draft-tokens",
|
|
"4",
|
|
"--mem-fraction-static",
|
|
"0.7",
|
|
"--page-size",
|
|
"256",
|
|
]
|
|
env_overrides = [
|
|
("SGLANG_TEST_RETRACT", True),
|
|
("SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN", True),
|
|
]
|
|
|
|
|
|
class TestStreamingSessionAbortLeakRepro(
|
|
StreamingSessionServerBase, AbortLeakReproKitMixin
|
|
):
|
|
extra_args = [
|
|
"--chunked-prefill-size",
|
|
str(ABORT_REPRO_CHUNKED_PREFILL_SIZE),
|
|
"--context-length",
|
|
str(ABORT_REPRO_CONTEXT_LEN),
|
|
"--page-size",
|
|
str(ABORT_REPRO_PAGE_SIZE),
|
|
"--max-running-requests",
|
|
"32",
|
|
"--log-level",
|
|
"info",
|
|
]
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|