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
83 lines
3.1 KiB
Python
83 lines
3.1 KiB
Python
import argparse
|
|
|
|
from sglang.auto_benchmark_lib import (
|
|
SUPPORTED_DATASETS,
|
|
convert_dataset,
|
|
run_auto_benchmark,
|
|
validate_dataset,
|
|
)
|
|
|
|
|
|
def add_dataset_args(parser: argparse.ArgumentParser) -> None:
|
|
parser.add_argument(
|
|
"--kind",
|
|
required=True,
|
|
choices=sorted(SUPPORTED_DATASETS),
|
|
help="Dataset kind: sharegpt, custom, random, or generated-shared-prefix.",
|
|
)
|
|
parser.add_argument(
|
|
"--path",
|
|
default="",
|
|
help="Dataset file path. Leave empty for sharegpt auto-download.",
|
|
)
|
|
parser.add_argument("--tokenizer", required=True)
|
|
parser.add_argument("--model", default=None)
|
|
parser.add_argument("--num-prompts", type=int, default=1000)
|
|
parser.add_argument("--output-len", type=int, default=None)
|
|
parser.add_argument("--context-len", type=int, default=None)
|
|
parser.add_argument("--prompt-suffix", type=str, default="")
|
|
parser.add_argument("--apply-chat-template", action="store_true")
|
|
parser.add_argument("--random-input-len", type=int, default=1024)
|
|
parser.add_argument("--random-output-len", type=int, default=256)
|
|
parser.add_argument("--random-range-ratio", type=float, default=0.0)
|
|
parser.add_argument("--gsp-num-groups", type=int, default=64)
|
|
parser.add_argument("--gsp-prompts-per-group", type=int, default=16)
|
|
parser.add_argument("--gsp-system-prompt-len", type=int, default=2048)
|
|
parser.add_argument("--gsp-question-len", type=int, default=128)
|
|
parser.add_argument("--gsp-output-len", type=int, default=256)
|
|
parser.add_argument("--gsp-range-ratio", type=float, default=1.0)
|
|
parser.add_argument("--gsp-fast-prepare", action="store_true")
|
|
parser.add_argument("--gsp-send-routing-key", action="store_true")
|
|
parser.add_argument("--gsp-num-turns", type=int, default=1)
|
|
parser.add_argument("--gsp-ordered", action="store_true")
|
|
parser.add_argument("--seed", type=int, default=1)
|
|
|
|
|
|
def build_parser() -> argparse.ArgumentParser:
|
|
parser = argparse.ArgumentParser(description="SGLang auto benchmark utilities.")
|
|
subparsers = parser.add_subparsers(dest="command", required=True)
|
|
|
|
run_parser = subparsers.add_parser(
|
|
"run", help="Run auto benchmark from YAML config."
|
|
)
|
|
run_parser.add_argument("--config", required=True)
|
|
|
|
convert_parser = subparsers.add_parser(
|
|
"convert",
|
|
help="Prepare sharegpt/custom/random/generated-shared-prefix data into canonical autobench JSONL.",
|
|
)
|
|
add_dataset_args(convert_parser)
|
|
convert_parser.add_argument("--output", required=True)
|
|
|
|
validate_parser = subparsers.add_parser(
|
|
"validate", help="Validate a canonical autobench JSONL dataset."
|
|
)
|
|
validate_parser.add_argument("--dataset-path", required=True)
|
|
validate_parser.add_argument("--tokenizer", required=True)
|
|
|
|
return parser
|
|
|
|
|
|
def main() -> None:
|
|
args = build_parser().parse_args()
|
|
if args.command == "run":
|
|
run_auto_benchmark(args.config)
|
|
elif args.command == "convert":
|
|
convert_dataset(args)
|
|
elif args.command == "validate":
|
|
validate_dataset(args)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|