Remove all references to yapf as it's no longer used (#26251)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-10-05 09:18:11 -07:00
committed by GitHub
parent d6953beb91
commit 4e256cadc2
78 changed files with 1992 additions and 1717 deletions
@@ -14,8 +14,6 @@ import vllm.envs as envs
import vllm.model_executor.layers.fused_moe.modular_kernel as mk
from vllm import _custom_ops as ops
from vllm.logger import init_logger
# yapf: disable
from vllm.model_executor.layers.fused_moe.config import (
FUSED_MOE_UNQUANTIZED_CONFIG,
FusedMoEQuantConfig,
@@ -25,8 +23,6 @@ from vllm.model_executor.layers.fused_moe.cutlass_moe import (
_valid_cutlass_block_scaled_grouped_gemm,
run_cutlass_block_scaled_fused_experts,
)
# yapf: enable
from vllm.model_executor.layers.fused_moe.deep_gemm_moe import (
_valid_deep_gemm,
deep_gemm_moe_fp8,
@@ -24,8 +24,6 @@ from vllm.distributed.eplb.eplb_state import EplbState
from vllm.forward_context import ForwardContext, get_forward_context
from vllm.logger import init_logger
from vllm.model_executor.custom_op import CustomOp
# yapf: disable
from vllm.model_executor.layers.fused_moe.config import (
FUSED_MOE_UNQUANTIZED_CONFIG,
FusedMoEConfig,
@@ -34,8 +32,6 @@ from vllm.model_executor.layers.fused_moe.config import (
biased_moe_quant_config,
)
from vllm.model_executor.layers.fused_moe.fused_moe import zero_experts_compute_triton
# yapf: enable
from vllm.model_executor.layers.fused_moe.modular_kernel import (
FusedMoEActivationFormat,
FusedMoEModularKernel,
@@ -10,7 +10,7 @@ import torch
import vllm.envs as envs
from vllm.model_executor.layers.fused_moe.config import FusedMoEQuantConfig
from vllm.model_executor.layers.fused_moe.utils import ( # yapf: disable
from vllm.model_executor.layers.fused_moe.utils import (
_resize_cache,
count_expert_num_tokens,
)
-4
View File
@@ -24,8 +24,6 @@ from vllm.model_executor.layers.quantization.base_config import (
QuantizeMethodBase,
)
from vllm.model_executor.layers.utils import dispatch_unquantized_gemm
# yapf: disable
from vllm.model_executor.parameter import (
BasevLLMParameter,
BlockQuantScaleParameter,
@@ -35,8 +33,6 @@ from vllm.model_executor.parameter import (
PerTensorScaleParameter,
RowvLLMParameter,
)
# yapf: enable
from vllm.model_executor.utils import set_weight_attrs
from vllm.platforms import current_platform
from vllm.utils import GiB_bytes
@@ -17,17 +17,12 @@ from vllm.model_executor.layers.quantization.kernels.mixed_precision import (
from vllm.model_executor.layers.quantization.utils.marlin_utils import (
marlin_repeat_scales_on_all_ranks,
)
# yapf conflicts with isort for this block
# yapf: disable
from vllm.model_executor.parameter import (
BasevLLMParameter,
ChannelQuantScaleParameter,
GroupQuantScaleParameter,
PackedvLLMParameter,
)
# yapf: enable
from vllm.scalar_type import scalar_types
logger = init_logger(__name__)
@@ -17,9 +17,6 @@ from vllm.model_executor.layers.quantization.kernels.mixed_precision import (
from vllm.model_executor.layers.quantization.utils.marlin_utils import (
marlin_repeat_scales_on_all_ranks,
)
# yapf conflicts with isort for this block
# yapf: disable
from vllm.model_executor.parameter import (
BasevLLMParameter,
ChannelQuantScaleParameter,
@@ -28,8 +25,6 @@ from vllm.model_executor.parameter import (
PackedvLLMParameter,
RowvLLMParameter,
)
# yapf: enable
from vllm.scalar_type import scalar_types
logger = init_logger(__name__)