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
293 lines
7.3 KiB
Python
293 lines
7.3 KiB
Python
"""Public APIs of the language."""
|
|
|
|
import re
|
|
from typing import Callable, List, Optional, Union
|
|
|
|
from sglang.global_config import global_config
|
|
from sglang.lang.backend.base_backend import BaseBackend
|
|
from sglang.lang.choices import ChoicesSamplingMethod, token_length_normalized
|
|
from sglang.lang.ir import (
|
|
SglExpr,
|
|
SglExprList,
|
|
SglFunction,
|
|
SglGen,
|
|
SglImage,
|
|
SglRoleBegin,
|
|
SglRoleEnd,
|
|
SglSelect,
|
|
SglSeparateReasoning,
|
|
SglVideo,
|
|
)
|
|
|
|
|
|
def function(
|
|
func: Optional[Callable] = None, num_api_spec_tokens: Optional[int] = None
|
|
):
|
|
if func:
|
|
return SglFunction(func, num_api_spec_tokens=num_api_spec_tokens)
|
|
|
|
def decorator(func):
|
|
return SglFunction(func, num_api_spec_tokens=num_api_spec_tokens)
|
|
|
|
return decorator
|
|
|
|
|
|
def Runtime(*args, **kwargs):
|
|
# Avoid importing unnecessary dependency
|
|
from sglang.lang.backend.runtime_endpoint import Runtime
|
|
|
|
return Runtime(*args, **kwargs)
|
|
|
|
|
|
def Engine(*args, **kwargs):
|
|
# Avoid importing unnecessary dependency
|
|
from sglang.srt.entrypoints.engine import Engine
|
|
|
|
return Engine(*args, **kwargs)
|
|
|
|
|
|
def set_default_backend(backend: BaseBackend):
|
|
global_config.default_backend = backend
|
|
|
|
|
|
def flush_cache(backend: Optional[BaseBackend] = None):
|
|
backend = backend or global_config.default_backend
|
|
if backend is None:
|
|
return False
|
|
|
|
# If backend is Runtime
|
|
if hasattr(backend, "endpoint"):
|
|
backend = backend.endpoint
|
|
return backend.flush_cache()
|
|
|
|
|
|
def get_server_info(backend: Optional[BaseBackend] = None):
|
|
backend = backend or global_config.default_backend
|
|
if backend is None:
|
|
return None
|
|
|
|
# If backend is Runtime
|
|
if hasattr(backend, "endpoint"):
|
|
backend = backend.endpoint
|
|
return backend.get_server_info()
|
|
|
|
|
|
def gen(
|
|
name: Optional[str] = None,
|
|
max_tokens: Optional[int] = None,
|
|
min_tokens: Optional[int] = None,
|
|
n: Optional[int] = None,
|
|
stop: Optional[Union[str, List[str]]] = None,
|
|
stop_token_ids: Optional[List[int]] = None,
|
|
stop_regex: Optional[Union[str, List[str]]] = None,
|
|
temperature: Optional[float] = None,
|
|
top_p: Optional[float] = None,
|
|
top_k: Optional[int] = None,
|
|
min_p: Optional[float] = None,
|
|
frequency_penalty: Optional[float] = None,
|
|
presence_penalty: Optional[float] = None,
|
|
ignore_eos: Optional[bool] = None,
|
|
return_logprob: Optional[bool] = None,
|
|
logprob_start_len: Optional[int] = None,
|
|
top_logprobs_num: Optional[int] = None,
|
|
return_text_in_logprobs: Optional[bool] = None,
|
|
dtype: Optional[Union[type, str]] = None,
|
|
choices: Optional[List[str]] = None,
|
|
choices_method: Optional[ChoicesSamplingMethod] = None,
|
|
regex: Optional[str] = None,
|
|
json_schema: Optional[str] = None,
|
|
):
|
|
"""Call the model to generate. See the meaning of the arguments in docs/backend/sampling_params.md"""
|
|
|
|
if choices:
|
|
return SglSelect(
|
|
name,
|
|
choices,
|
|
0.0 if temperature is None else temperature,
|
|
token_length_normalized if choices_method is None else choices_method,
|
|
)
|
|
|
|
# check regex is valid
|
|
if regex is not None:
|
|
try:
|
|
re.compile(regex)
|
|
except re.error as e:
|
|
raise e
|
|
|
|
return SglGen(
|
|
name,
|
|
max_tokens,
|
|
min_tokens,
|
|
n,
|
|
stop,
|
|
stop_token_ids,
|
|
stop_regex,
|
|
temperature,
|
|
top_p,
|
|
top_k,
|
|
min_p,
|
|
frequency_penalty,
|
|
presence_penalty,
|
|
ignore_eos,
|
|
return_logprob,
|
|
logprob_start_len,
|
|
top_logprobs_num,
|
|
return_text_in_logprobs,
|
|
dtype,
|
|
regex,
|
|
json_schema,
|
|
)
|
|
|
|
|
|
def gen_int(
|
|
name: Optional[str] = None,
|
|
max_tokens: Optional[int] = None,
|
|
n: Optional[int] = None,
|
|
stop: Optional[Union[str, List[str]]] = None,
|
|
stop_token_ids: Optional[List[int]] = None,
|
|
stop_regex: Optional[Union[str, List[str]]] = None,
|
|
temperature: Optional[float] = None,
|
|
top_p: Optional[float] = None,
|
|
top_k: Optional[int] = None,
|
|
min_p: Optional[float] = None,
|
|
frequency_penalty: Optional[float] = None,
|
|
presence_penalty: Optional[float] = None,
|
|
ignore_eos: Optional[bool] = None,
|
|
return_logprob: Optional[bool] = None,
|
|
logprob_start_len: Optional[int] = None,
|
|
top_logprobs_num: Optional[int] = None,
|
|
return_text_in_logprobs: Optional[bool] = None,
|
|
):
|
|
return SglGen(
|
|
name,
|
|
max_tokens,
|
|
None,
|
|
n,
|
|
stop,
|
|
stop_token_ids,
|
|
stop_regex,
|
|
temperature,
|
|
top_p,
|
|
top_k,
|
|
min_p,
|
|
frequency_penalty,
|
|
presence_penalty,
|
|
ignore_eos,
|
|
return_logprob,
|
|
logprob_start_len,
|
|
top_logprobs_num,
|
|
return_text_in_logprobs,
|
|
int,
|
|
None,
|
|
)
|
|
|
|
|
|
def gen_string(
|
|
name: Optional[str] = None,
|
|
max_tokens: Optional[int] = None,
|
|
n: Optional[int] = None,
|
|
stop: Optional[Union[str, List[str]]] = None,
|
|
stop_token_ids: Optional[List[int]] = None,
|
|
stop_regex: Optional[Union[str, List[str]]] = None,
|
|
temperature: Optional[float] = None,
|
|
top_p: Optional[float] = None,
|
|
top_k: Optional[int] = None,
|
|
min_p: Optional[float] = None,
|
|
frequency_penalty: Optional[float] = None,
|
|
presence_penalty: Optional[float] = None,
|
|
ignore_eos: Optional[bool] = None,
|
|
return_logprob: Optional[bool] = None,
|
|
logprob_start_len: Optional[int] = None,
|
|
top_logprobs_num: Optional[int] = None,
|
|
return_text_in_logprobs: Optional[bool] = None,
|
|
):
|
|
return SglGen(
|
|
name,
|
|
max_tokens,
|
|
None,
|
|
n,
|
|
stop,
|
|
stop_token_ids,
|
|
stop_regex,
|
|
temperature,
|
|
top_p,
|
|
top_k,
|
|
min_p,
|
|
frequency_penalty,
|
|
presence_penalty,
|
|
ignore_eos,
|
|
return_logprob,
|
|
logprob_start_len,
|
|
top_logprobs_num,
|
|
return_text_in_logprobs,
|
|
str,
|
|
None,
|
|
)
|
|
|
|
|
|
def image(expr: SglExpr):
|
|
return SglImage(expr)
|
|
|
|
|
|
def video(path: str, num_frames: int):
|
|
return SglVideo(path, num_frames)
|
|
|
|
|
|
def select(
|
|
name: Optional[str] = None,
|
|
choices: Optional[List[str]] = None,
|
|
temperature: float = 0.0,
|
|
choices_method: ChoicesSamplingMethod = token_length_normalized,
|
|
):
|
|
assert choices is not None
|
|
return SglSelect(name, choices, temperature, choices_method)
|
|
|
|
|
|
def _role_common(name: str, expr: Optional[SglExpr] = None):
|
|
if expr is None:
|
|
return SglExprList([SglRoleBegin(name), SglRoleEnd(name)])
|
|
else:
|
|
return SglExprList([SglRoleBegin(name), expr, SglRoleEnd(name)])
|
|
|
|
|
|
def system(expr: Optional[SglExpr] = None):
|
|
return _role_common("system", expr)
|
|
|
|
|
|
def user(expr: Optional[SglExpr] = None):
|
|
return _role_common("user", expr)
|
|
|
|
|
|
def assistant(expr: Optional[SglExpr] = None):
|
|
return _role_common("assistant", expr)
|
|
|
|
|
|
def system_begin():
|
|
return SglRoleBegin("system")
|
|
|
|
|
|
def system_end():
|
|
return SglRoleEnd("system")
|
|
|
|
|
|
def user_begin():
|
|
return SglRoleBegin("user")
|
|
|
|
|
|
def user_end():
|
|
return SglRoleEnd("user")
|
|
|
|
|
|
def assistant_begin():
|
|
return SglRoleBegin("assistant")
|
|
|
|
|
|
def assistant_end():
|
|
return SglRoleEnd("assistant")
|
|
|
|
|
|
def separate_reasoning(
|
|
expr: Optional[SglExpr] = None, model_type: Optional[str] = None
|
|
):
|
|
return SglExprList([expr, SglSeparateReasoning(model_type, expr=expr)])
|