[Chore]:Extract math and argparse utilities to separate modules (#27188)

Signed-off-by: Yeshwanth Surya <yeshsurya@gmail.com>
Signed-off-by: Yeshwanth N <yeshsurya@gmail.com>
Signed-off-by: yeshsurya <yeshsurya@gmail.com>

vllm/v1/kv_cache_interface.py

@@ -10,7 +10,7 @@ from typing_extensions import Self
 
 from vllm.config import VllmConfig
 from vllm.logger import init_logger
-from vllm.utils import cdiv
+from vllm.utils.math_utils import cdiv
 from vllm.utils.torch_utils import get_dtype_size
 
 logger = init_logger(__name__)

vllm/v1/worker/block_table.py

@@ -6,7 +6,7 @@ import torch
 
 from vllm.distributed import get_dcp_group
 from vllm.logger import init_logger
-from vllm.utils import cdiv
+from vllm.utils.math_utils import cdiv
 from vllm.v1.utils import CpuGpuBuffer
 
 logger = init_logger(__name__)

vllm/v1/worker/gpu_model_runner.py

@@ -70,12 +70,11 @@ from vllm.sampling_params import SamplingType
 from vllm.sequence import IntermediateTensors
 from vllm.tasks import GenerationTask, PoolingTask, SupportedTask
 from vllm.utils import (
-    cdiv,
     check_use_alibi,
     length_from_prompt_token_ids_or_embeds,
-    round_up,
 )
 from vllm.utils.jsontree import json_map_leaves
+from vllm.utils.math_utils import cdiv, round_up
 from vllm.utils.mem_constants import GiB_bytes
 from vllm.utils.mem_utils import DeviceMemoryProfiler
 from vllm.utils.platform_utils import is_pin_memory_available

vllm/v1/worker/tpu_model_runner.py

@@ -53,7 +53,8 @@ from vllm.multimodal.inputs import (
 from vllm.multimodal.utils import group_mm_kwargs_by_modality
 from vllm.sequence import IntermediateTensors
 from vllm.tasks import GenerationTask, PoolingTask, SupportedTask
-from vllm.utils import LayerBlockType, cdiv, prev_power_of_2
+from vllm.utils import LayerBlockType
+from vllm.utils.math_utils import cdiv, prev_power_of_2
 from vllm.utils.platform_utils import is_pin_memory_available
 from vllm.v1.attention.backends.pallas import (
     TPU_STR_DTYPE_TO_TORCH_DTYPE,

vllm/v1/worker/tpu_worker.py

@@ -25,7 +25,7 @@ from vllm.model_executor import set_random_seed
 from vllm.platforms import current_platform
 from vllm.platforms.tpu import USE_TPU_INFERENCE
 from vllm.tasks import SupportedTask
-from vllm.utils import cdiv
+from vllm.utils.math_utils import cdiv
 from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE
 from vllm.v1.core.sched.output import SchedulerOutput
 from vllm.v1.kv_cache_interface import AttentionSpec, KVCacheConfig, KVCacheSpec