- Keep only Qwen3.5, Qwen3.5-MTP and Qwen4Exp model paths; trim the model registry to 41 entries - Delete idle attention backends (MLA, FlashInfer, ROCm-only, quant backends) and dead GDN CuTeDSL kernels - Remove inc/quark quant loaders; keep compressed-tensors and Marlin - Drop the Rust frontend, pooling entrypoints, and idle test suites - Rebuild kernels for sm_80;sm_86 and strip the extensions - Verified: full import sweep clean (optional deps only) and a dummy-load Qwen3.5 engine run on RTX 3090 via the Triton GDN path Co-authored-by: Hinata <hinata@idihore.id> Signed-off-by: MOVZX <movzx@yahoo.com>
41 lines
960 B
Python
41 lines
960 B
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
"""Qwen4Exp model package."""
|
|
|
|
from typing import TYPE_CHECKING, Any
|
|
|
|
from .common.hyperconnection import (
|
|
GatedResidual,
|
|
GroupedGemmaRMSNorm,
|
|
HyperConnectionBase,
|
|
HyperConnectionConfig,
|
|
)
|
|
|
|
if TYPE_CHECKING:
|
|
from .nvidia.model import (
|
|
Qwen4ExpForCausalLM,
|
|
Qwen4ExpForConditionalGeneration,
|
|
)
|
|
from .nvidia.mtp import Qwen4ExpMTP
|
|
|
|
|
|
def __getattr__(name: str) -> Any:
|
|
from .nvidia import model as _nvidia_model
|
|
from .nvidia import mtp as _nvidia_mtp
|
|
|
|
for mod in (_nvidia_model, _nvidia_mtp):
|
|
if hasattr(mod, name):
|
|
return getattr(mod, name)
|
|
raise AttributeError(name)
|
|
|
|
|
|
__all__ = [
|
|
"GatedResidual",
|
|
"GroupedGemmaRMSNorm",
|
|
"HyperConnectionBase",
|
|
"HyperConnectionConfig",
|
|
"Qwen4ExpForCausalLM",
|
|
"Qwen4ExpForConditionalGeneration",
|
|
"Qwen4ExpMTP",
|
|
]
|