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
122 lines
4.2 KiB
Python
122 lines
4.2 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
"""CLI- and API-facing configuration for diffusion post-training / rollout paths."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import math
|
|
from dataclasses import dataclass
|
|
from typing import Any, Callable
|
|
|
|
from sglang.multimodal_gen.utils import StoreBoolean
|
|
|
|
_VALID_ROLLOUT_SDE_TYPES = ("sde", "cps", "ode")
|
|
|
|
|
|
@dataclass
|
|
class RLRolloutArgs:
|
|
"""Rollout (log-prob trajectory) options used by SamplingParams and APIs."""
|
|
|
|
rollout: bool = False
|
|
rollout_sde_type: str = "sde"
|
|
rollout_noise_level: float = 0.7
|
|
rollout_log_prob_no_const: bool = False
|
|
rollout_debug_mode: bool = False
|
|
|
|
def validate(self) -> None:
|
|
noise = self.rollout_noise_level
|
|
if isinstance(noise, bool) or not isinstance(noise, (int, float)):
|
|
raise ValueError(f"rollout_noise_level must be a number, got {noise!r}")
|
|
if not math.isfinite(float(noise)):
|
|
raise ValueError(f"rollout_noise_level must be finite, got {noise!r}")
|
|
if float(noise) < 0.0:
|
|
raise ValueError(f"rollout_noise_level must be non-negative, got {noise!r}")
|
|
|
|
if self.rollout_sde_type not in _VALID_ROLLOUT_SDE_TYPES:
|
|
raise ValueError(
|
|
f"rollout_sde_type must be one of {_VALID_ROLLOUT_SDE_TYPES}, "
|
|
f"got {self.rollout_sde_type!r}"
|
|
)
|
|
|
|
@classmethod
|
|
def validate_sampling_params(cls, params: Any) -> None:
|
|
"""Validate rollout fields on a duck-typed object (e.g. ``SamplingParams``).
|
|
|
|
Mirrors how ``ServerArgs`` runs ``NunchakuSVDQuantArgs.validate()`` from
|
|
``_adjust_quant_config`` instead of inlining checks in a large validator.
|
|
"""
|
|
cls(
|
|
rollout=params.rollout,
|
|
rollout_sde_type=params.rollout_sde_type,
|
|
rollout_noise_level=params.rollout_noise_level,
|
|
rollout_log_prob_no_const=params.rollout_log_prob_no_const,
|
|
rollout_debug_mode=params.rollout_debug_mode,
|
|
).validate()
|
|
|
|
@staticmethod
|
|
def add_cli_args(
|
|
parser: Any,
|
|
add_argument: Callable[..., Any] | None = None,
|
|
) -> None:
|
|
"""Register rollout-related CLI flags on ``parser``.
|
|
|
|
If ``add_argument`` is provided (e.g. SamplingParams' wrapper with
|
|
``default=argparse.SUPPRESS``), it is used; otherwise a local wrapper
|
|
is applied.
|
|
"""
|
|
|
|
if add_argument is None:
|
|
|
|
def _add(*name_or_flags: Any, **kwargs: Any):
|
|
kwargs.setdefault("default", argparse.SUPPRESS)
|
|
return parser.add_argument(*name_or_flags, **kwargs)
|
|
|
|
add_argument = _add
|
|
|
|
add_argument(
|
|
"--rollout",
|
|
action="store_true",
|
|
help="Enable rollout mode and return per-step log_prob trajectory",
|
|
)
|
|
add_argument(
|
|
"--rollout-sde-type",
|
|
type=str,
|
|
choices=list(_VALID_ROLLOUT_SDE_TYPES),
|
|
help="Rollout step objective type used in log-prob computation.",
|
|
)
|
|
add_argument(
|
|
"--rollout-noise-level",
|
|
type=float,
|
|
help="Noise level used by rollout SDE/CPS step objective.",
|
|
)
|
|
add_argument(
|
|
"--rollout-log-prob-no-const",
|
|
action=StoreBoolean,
|
|
help="If true, return rollout log-prob without constant terms.",
|
|
)
|
|
add_argument(
|
|
"--rollout-debug-mode",
|
|
action=StoreBoolean,
|
|
help=(
|
|
"If true, return rollout debug tensors "
|
|
"(variance noise, mean, std, model output)."
|
|
),
|
|
)
|
|
|
|
@classmethod
|
|
def from_dict(cls, kwargs: dict[str, Any]) -> RLRolloutArgs:
|
|
return cls(
|
|
rollout=bool(kwargs.get("rollout", cls.rollout)),
|
|
rollout_sde_type=str(kwargs.get("rollout_sde_type", cls.rollout_sde_type)),
|
|
rollout_noise_level=float(
|
|
kwargs.get("rollout_noise_level", cls.rollout_noise_level)
|
|
),
|
|
rollout_log_prob_no_const=bool(
|
|
kwargs.get("rollout_log_prob_no_const", cls.rollout_log_prob_no_const)
|
|
),
|
|
rollout_debug_mode=bool(
|
|
kwargs.get("rollout_debug_mode", cls.rollout_debug_mode)
|
|
),
|
|
)
|