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
71 lines
2.1 KiB
Python
71 lines
2.1 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
from dataclasses import dataclass, field
|
|
|
|
from sglang.multimodal_gen.configs.models.vaes.base import VAEArchConfig, VAEConfig
|
|
|
|
|
|
@dataclass
|
|
class FluxVAEArchConfig(VAEArchConfig):
|
|
spatial_compression_ratio: int = 1
|
|
|
|
base_dim: int = 96
|
|
decoder_base_dim: int | None = None
|
|
z_dim: int = 16
|
|
dim_mult: tuple[int, ...] = (1, 2, 4, 4)
|
|
num_res_blocks: int = 2
|
|
attn_scales: tuple[float, ...] = ()
|
|
temperal_downsample: tuple[bool, ...] = (False, True, True)
|
|
dropout: float = 0.0
|
|
|
|
is_residual: bool = False
|
|
in_channels: int = 3
|
|
out_channels: int = 3
|
|
patch_size: int | None = None
|
|
scale_factor_temporal: int = 4
|
|
scale_factor_spatial: int = 8
|
|
clip_output: bool = True
|
|
|
|
|
|
@dataclass
|
|
class Flux2VAEArchConfig(FluxVAEArchConfig):
|
|
decoder_block_out_channels: tuple[int, ...] | None = None
|
|
|
|
|
|
@dataclass
|
|
class FluxVAEConfig(VAEConfig):
|
|
arch_config: FluxVAEArchConfig = field(default_factory=FluxVAEArchConfig)
|
|
|
|
use_feature_cache: bool = True
|
|
|
|
use_tiling: bool = False
|
|
use_temporal_tiling: bool = False
|
|
use_parallel_tiling: bool = False
|
|
|
|
def __post_init__(self):
|
|
self.blend_num_frames = (
|
|
self.tile_sample_min_num_frames - self.tile_sample_stride_num_frames
|
|
) * 2
|
|
|
|
def post_init(self):
|
|
# Calculate vae_scale_factor: prefer block_out_channels, fallback to dim_mult or scale_factor_spatial
|
|
if (
|
|
hasattr(self.arch_config, "block_out_channels")
|
|
and self.arch_config.block_out_channels
|
|
):
|
|
self.arch_config.vae_scale_factor = 2 ** (
|
|
len(self.arch_config.block_out_channels) - 1
|
|
)
|
|
elif self.arch_config.dim_mult:
|
|
self.arch_config.vae_scale_factor = 2 ** (
|
|
len(self.arch_config.dim_mult) - 1
|
|
)
|
|
else:
|
|
self.arch_config.vae_scale_factor = self.arch_config.scale_factor_spatial
|
|
|
|
self.arch_config.spatial_compression_ratio = self.arch_config.vae_scale_factor
|
|
|
|
|
|
@dataclass
|
|
class Flux2VAEConfig(FluxVAEConfig):
|
|
arch_config: Flux2VAEArchConfig = field(default_factory=Flux2VAEArchConfig)
|