[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: isotr0py <2037008807@qq.com>
This commit is contained in:
Isotr0py
2025-10-18 09:48:22 -07:00
committed by GitHub
parent 5c2acb270a
commit 6ac5e06f7c
119 changed files with 772 additions and 714 deletions
@@ -10,7 +10,8 @@ import torch
from vllm.model_executor.layers.quantization.input_quant_fp8 import QuantFP8
from vllm.model_executor.layers.quantization.utils.quant_utils import GroupShape
from vllm.triton_utils import triton
from vllm.utils import STR_DTYPE_TO_TORCH_DTYPE, FlexibleArgumentParser
from vllm.utils import FlexibleArgumentParser
from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE
def with_triton_mode(fn):
+2 -1
View File
@@ -10,7 +10,8 @@ import vllm.model_executor.layers.activation # noqa F401
from vllm.model_executor.custom_op import CustomOp
from vllm.platforms import current_platform
from vllm.triton_utils import triton
from vllm.utils import STR_DTYPE_TO_TORCH_DTYPE, FlexibleArgumentParser
from vllm.utils import FlexibleArgumentParser
from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE
batch_size_range = [1, 16, 32, 64, 128]
seq_len_range = [1, 16, 64, 128, 256, 512, 1024, 2048, 4096]
+2 -1
View File
@@ -7,7 +7,8 @@ import torch
from vllm.model_executor.layers.layernorm import RMSNorm
from vllm.platforms import current_platform
from vllm.utils import STR_DTYPE_TO_TORCH_DTYPE, FlexibleArgumentParser
from vllm.utils import FlexibleArgumentParser
from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE
@torch.inference_mode()
@@ -9,9 +9,9 @@ import torch
from vllm import _custom_ops as ops
from vllm.logger import init_logger
from vllm.platforms import current_platform
from vllm.utils import (
from vllm.utils import FlexibleArgumentParser
from vllm.utils.torch_utils import (
STR_DTYPE_TO_TORCH_DTYPE,
FlexibleArgumentParser,
create_kv_caches_with_random,
)
+2 -1
View File
@@ -7,7 +7,8 @@ import torch
from vllm import _custom_ops as ops
from vllm.platforms import current_platform
from vllm.utils import STR_DTYPE_TO_TORCH_DTYPE, FlexibleArgumentParser
from vllm.utils import FlexibleArgumentParser
from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE
@torch.inference_mode()
@@ -9,9 +9,9 @@ from tabulate import tabulate
from vllm import _custom_ops as ops
from vllm.logger import init_logger
from vllm.platforms import current_platform
from vllm.utils import (
from vllm.utils import FlexibleArgumentParser
from vllm.utils.torch_utils import (
STR_DTYPE_TO_TORCH_DTYPE,
FlexibleArgumentParser,
create_kv_caches_with_random,
)
@@ -12,9 +12,9 @@ from vllm.attention.ops.triton_reshape_and_cache_flash import (
)
from vllm.logger import init_logger
from vllm.platforms import current_platform
from vllm.utils import (
from vllm.utils import FlexibleArgumentParser
from vllm.utils.torch_utils import (
STR_DTYPE_TO_TORCH_DTYPE,
FlexibleArgumentParser,
create_kv_caches_with_random_flash,
)