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
144 lines
5.0 KiB
Python
144 lines
5.0 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
import argparse
|
|
import logging
|
|
import os
|
|
|
|
from sglang.cli.utils import get_is_diffusion_model, get_model_path
|
|
from sglang.srt.utils import kill_process_tree
|
|
from sglang.srt.utils.common import suppress_noisy_warnings
|
|
|
|
suppress_noisy_warnings()
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def _extract_model_type_override(extra_argv):
|
|
"""Extract and remove --model-type override from argv."""
|
|
model_type = "auto"
|
|
filtered_argv = []
|
|
i = 0
|
|
while i < len(extra_argv):
|
|
arg = extra_argv[i]
|
|
if arg == "--model-type":
|
|
if i + 1 >= len(extra_argv):
|
|
raise Exception(
|
|
"Error: --model-type requires a value. "
|
|
"Valid values are: auto, llm, diffusion."
|
|
)
|
|
model_type = extra_argv[i + 1]
|
|
i += 2
|
|
continue
|
|
|
|
if arg.startswith("--model-type="):
|
|
model_type = arg.split("=", 1)[1]
|
|
i += 1
|
|
continue
|
|
|
|
filtered_argv.append(arg)
|
|
i += 1
|
|
|
|
if model_type not in ("auto", "llm", "diffusion"):
|
|
raise Exception(
|
|
f"Error: invalid --model-type '{model_type}'. "
|
|
"Valid values are: auto, llm, diffusion."
|
|
)
|
|
return model_type, filtered_argv
|
|
|
|
|
|
def _normalize_positional_model_path(extra_argv):
|
|
"""Allow `sglang serve <model>` while preserving existing flag parsing."""
|
|
if extra_argv and not extra_argv[0].startswith("-"):
|
|
return ["--model-path", extra_argv[0], *extra_argv[1:]], True
|
|
return extra_argv, False
|
|
|
|
|
|
def serve(args, extra_argv):
|
|
if any(h in extra_argv for h in ("-h", "--help")):
|
|
# Since the server type is determined by the model, and we don't have a model path,
|
|
# we can't show the exact help. Instead, we show a general help message and then
|
|
# the help for both possible server types.
|
|
print(
|
|
"Usage: sglang serve <model-name-or-path> [additional-arguments]\n"
|
|
" or: sglang serve --model-path <model-name-or-path> [additional-arguments]\n\n"
|
|
"This command can launch either a standard language model server or a diffusion model server.\n"
|
|
"The server type is determined by the --model-path.\n"
|
|
"Optional override: --model-type {auto,llm,diffusion} "
|
|
"(default: auto, fallback to LLM on detection failure)."
|
|
)
|
|
|
|
print("\n--- Help for Standard Language Model Server ---")
|
|
from sglang.srt.server_args import prepare_server_args
|
|
|
|
try:
|
|
prepare_server_args(["--help"])
|
|
except SystemExit:
|
|
pass # argparse --help calls sys.exit
|
|
|
|
print("\n--- Help for Diffusion Model Server ---")
|
|
try:
|
|
from sglang.multimodal_gen.runtime.entrypoints.cli.serve import (
|
|
add_multimodal_gen_serve_args,
|
|
)
|
|
|
|
parser = argparse.ArgumentParser(
|
|
prog="sglang serve",
|
|
description="SGLang Diffusion Model Serving",
|
|
)
|
|
add_multimodal_gen_serve_args(parser)
|
|
parser.print_help()
|
|
except ImportError:
|
|
print(
|
|
"Diffusion model support is not available. "
|
|
'Install with: pip install "sglang[diffusion]"'
|
|
)
|
|
return
|
|
|
|
from sglang.srt.plugins import load_plugins
|
|
|
|
load_plugins()
|
|
|
|
model_type, dispatch_argv = _extract_model_type_override(extra_argv)
|
|
dispatch_argv, positional_model_path = _normalize_positional_model_path(
|
|
dispatch_argv
|
|
)
|
|
model_path = get_model_path(dispatch_argv)
|
|
try:
|
|
if model_type == "auto":
|
|
is_diffusion_model = get_is_diffusion_model(model_path)
|
|
if is_diffusion_model:
|
|
logger.info("Diffusion model detected")
|
|
else:
|
|
is_diffusion_model = model_type == "diffusion"
|
|
logger.info(
|
|
"Dispatch override enabled: --model-type=%s " "(skip auto detection)",
|
|
model_type,
|
|
)
|
|
|
|
if is_diffusion_model:
|
|
# Logic for Diffusion Models
|
|
from sglang.multimodal_gen.runtime.entrypoints.cli.serve import (
|
|
add_multimodal_gen_serve_args,
|
|
execute_serve_cmd,
|
|
)
|
|
|
|
parser = argparse.ArgumentParser(
|
|
description="SGLang Diffusion Model Serving"
|
|
)
|
|
add_multimodal_gen_serve_args(parser)
|
|
parsed_args, remaining_argv = parser.parse_known_args(dispatch_argv)
|
|
if positional_model_path:
|
|
parsed_args._sglang_explicit_arg_names = {"model_path"}
|
|
|
|
execute_serve_cmd(parsed_args, remaining_argv)
|
|
else:
|
|
# Logic for Standard Language Models
|
|
from sglang.launch_server import run_server
|
|
from sglang.srt.server_args import prepare_server_args
|
|
|
|
server_args = prepare_server_args(dispatch_argv)
|
|
|
|
run_server(server_args)
|
|
finally:
|
|
kill_process_tree(os.getpid(), include_parent=False)
|