remove progress_bar imports

aphrodite/modeling/models/arctic.py

@@ -8,7 +8,6 @@ from torch import nn
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size,
                                    tensor_model_parallel_all_reduce)

aphrodite/modeling/models/baichuan.py

@@ -28,7 +28,6 @@ from transformers import PretrainedConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, LoRAConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size)
 from aphrodite.modeling.layers.activation import SiluAndMul

aphrodite/modeling/models/blip2.py

@@ -10,7 +10,6 @@ from aphrodite.attention import AttentionMetadata
 from aphrodite.common.config import CacheConfig, MultiModalConfig
 from aphrodite.common.sequence import (IntermediateTensors, SamplerOutput,
                                        SequenceData)
-from aphrodite.common.utils import progress_bar
 from aphrodite.inputs import INPUT_REGISTRY, InputContext, LLMInputs
 from aphrodite.modeling.layers.activation import get_act_fn
 from aphrodite.modeling.layers.logits_processor import LogitsProcessor

aphrodite/modeling/models/bloom.py

@@ -26,7 +26,6 @@ from transformers import BloomConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size)
 from aphrodite.modeling.layers.activation import get_act_fn

aphrodite/modeling/models/chameleon.py

@@ -12,7 +12,7 @@ from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, MultiModalConfig
 from aphrodite.common.sequence import (IntermediateTensors, SamplerOutput,
                                        SequenceData)
-from aphrodite.common.utils import print_warning_once, progress_bar
+from aphrodite.common.utils import print_warning_once
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.inputs import INPUT_REGISTRY, InputContext, LLMInputs
 from aphrodite.modeling.layers.activation import SiluAndMul

aphrodite/modeling/models/chatglm.py

@@ -11,7 +11,6 @@ from torch.nn import LayerNorm
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, LoRAConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import SiluAndMul
 from aphrodite.modeling.layers.layernorm import RMSNorm

aphrodite/modeling/models/commandr.py

@@ -30,7 +30,6 @@ from transformers import CohereConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, LoRAConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import SiluAndMul
 from aphrodite.modeling.layers.linear import (MergedColumnParallelLinear,

aphrodite/modeling/models/dbrx.py

@@ -7,7 +7,6 @@ import torch.nn as nn
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size,
                                    tensor_model_parallel_all_reduce)

aphrodite/modeling/models/decilm.py

@@ -29,7 +29,6 @@ import torch
 from transformers import LlamaConfig
 
 from aphrodite.common.config import CacheConfig, LoRAConfig
-from aphrodite.common.utils import progress_bar
 from aphrodite.modeling.model_loader.weight_utils import default_weight_loader
 from aphrodite.modeling.models.llama import LlamaForCausalLM
 from aphrodite.quantization.base_config import QuantizationConfig

aphrodite/modeling/models/deepseek.py

@@ -30,7 +30,6 @@ from transformers import PretrainedConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size,
                                    tensor_model_parallel_all_reduce)

aphrodite/modeling/models/deepseek_v2.py

@@ -31,7 +31,6 @@ from transformers import PretrainedConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_tensor_model_parallel_world_size,
                                    tensor_model_parallel_all_reduce)
 from aphrodite.modeling.layers.activation import SiluAndMul

aphrodite/modeling/models/exaone.py

@@ -31,7 +31,7 @@ from torch import nn
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, LoRAConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import is_hip, progress_bar
+from aphrodite.common.utils import is_hip
 from aphrodite.distributed import (get_pp_group,
                                    get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size)

aphrodite/modeling/models/falcon.py

@@ -29,7 +29,6 @@ from transformers import FalconConfig as HF_FalconConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size,
                                    tensor_model_parallel_all_reduce)

aphrodite/modeling/models/fuyu.py

@@ -28,7 +28,6 @@ from aphrodite.attention import AttentionMetadata
 from aphrodite.common.config import CacheConfig, MultiModalConfig
 from aphrodite.common.sequence import (IntermediateTensors, SamplerOutput,
                                        SequenceData)
-from aphrodite.common.utils import progress_bar
 from aphrodite.inputs import INPUT_REGISTRY, InputContext, LLMInputs
 from aphrodite.modeling.layers.linear import ColumnParallelLinear
 from aphrodite.modeling.model_loader.weight_utils import default_weight_loader

aphrodite/modeling/models/gemma.py

@@ -25,7 +25,6 @@ from transformers import GemmaConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, LoRAConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import GeluAndMul
 from aphrodite.modeling.layers.layernorm import GemmaRMSNorm

aphrodite/modeling/models/gemma2.py

@@ -25,7 +25,6 @@ from transformers import Gemma2Config
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, LoRAConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import GeluAndMul
 from aphrodite.modeling.layers.layernorm import GemmaRMSNorm

aphrodite/modeling/models/gpt2.py

@@ -26,7 +26,6 @@ from transformers import GPT2Config
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import get_act_fn
 from aphrodite.modeling.layers.linear import (ColumnParallelLinear,

aphrodite/modeling/models/gpt_bigcode.py

@@ -27,7 +27,6 @@ from transformers import GPTBigCodeConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import get_act_fn
 from aphrodite.modeling.layers.linear import (ColumnParallelLinear,

aphrodite/modeling/models/gpt_j.py

@@ -25,7 +25,6 @@ from transformers import GPTJConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import get_act_fn
 from aphrodite.modeling.layers.linear import (ColumnParallelLinear,

aphrodite/modeling/models/gpt_neox.py

@@ -25,7 +25,6 @@ from transformers import GPTNeoXConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import get_act_fn
 from aphrodite.modeling.layers.linear import (ColumnParallelLinear,

aphrodite/modeling/models/intern_vit.py

@@ -11,7 +11,6 @@ import torch.nn as nn
 import torch.nn.functional as F
 from transformers import PretrainedConfig
 
-from aphrodite.common.utils import progress_bar
 from aphrodite.modeling.layers.activation import get_act_fn
 from aphrodite.modeling.layers.layernorm import RMSNorm
 from aphrodite.modeling.layers.linear import (ColumnParallelLinear,

aphrodite/modeling/models/internlm2.py

@@ -8,7 +8,6 @@ from transformers import PretrainedConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import SiluAndMul
 from aphrodite.modeling.layers.layernorm import RMSNorm

aphrodite/modeling/models/jais.py

@@ -28,7 +28,6 @@ from torch import nn
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size)
 from aphrodite.modeling.layers.linear import (ColumnParallelLinear,

aphrodite/modeling/models/jamba.py

@@ -12,7 +12,6 @@ from aphrodite.attention.backends.abstract import AttentionMetadata
 from aphrodite.attention.layer import Attention
 from aphrodite.common.config import CacheConfig, LoRAConfig, SchedulerConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 # yapf: disable
 from aphrodite.distributed import (get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size)

aphrodite/modeling/models/llama_embedding.py

@@ -5,7 +5,6 @@ from torch import nn
 
 from aphrodite.attention import AttentionMetadata
 from aphrodite.common.sequence import PoolerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.modeling.layers.pooler import Pooler, PoolingType
 from aphrodite.modeling.model_loader.weight_utils import default_weight_loader
 from aphrodite.modeling.models.llama import LlamaModel

aphrodite/modeling/models/medusa.py

@@ -4,7 +4,6 @@ import torch
 import torch.nn as nn
 
 from aphrodite.common.sequence import SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.modeling.layers.logits_processor import LogitsProcessor
 from aphrodite.modeling.layers.vocab_parallel_embedding import (
     DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead)

aphrodite/modeling/models/minicpm.py

@@ -32,7 +32,6 @@ from transformers import PretrainedConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, LoRAConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size,
                                    tensor_model_parallel_all_reduce)

aphrodite/modeling/models/minicpmv.py

@@ -40,7 +40,6 @@ from aphrodite.attention import AttentionMetadata
 from aphrodite.common.config import CacheConfig, MultiModalConfig
 from aphrodite.common.sequence import (IntermediateTensors, SamplerOutput,
                                        SequenceData)
-from aphrodite.common.utils import progress_bar
 from aphrodite.inputs import INPUT_REGISTRY, InputContext, LLMInputs
 from aphrodite.modeling.layers.linear import ReplicatedLinear
 from aphrodite.modeling.layers.logits_processor import LogitsProcessor

aphrodite/modeling/models/mixtral.py

@@ -30,7 +30,6 @@ from transformers import MixtralConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, LoRAConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_pp_group,
                                    get_tensor_model_parallel_world_size)
 from aphrodite.modeling.layers.fused_moe import FusedMoE

aphrodite/modeling/models/mixtral_quant.py

@@ -32,7 +32,6 @@ from transformers import MixtralConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size,
                                    tensor_model_parallel_all_reduce)

aphrodite/modeling/models/mlp_speculator.py

@@ -5,7 +5,6 @@ import torch
 import torch.nn as nn
 
 from aphrodite.common.sequence import SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.modeling import SamplingMetadata
 from aphrodite.modeling.layers.logits_processor import LogitsProcessor
 from aphrodite.modeling.layers.sampler import Sampler

aphrodite/modeling/models/mpt.py

@@ -9,7 +9,6 @@ import torch.nn as nn
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size)
 from aphrodite.modeling.layers.activation import get_act_fn

aphrodite/modeling/models/nemotron.py

@@ -31,7 +31,6 @@ from transformers import NemotronConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, LoRAConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_pp_group,
                                    get_tensor_model_parallel_world_size)
 from aphrodite.modeling.layers.activation import get_act_fn

aphrodite/modeling/models/olmo.py

@@ -30,7 +30,6 @@ from transformers import OlmoConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import SiluAndMul
 from aphrodite.modeling.layers.linear import (MergedColumnParallelLinear,

aphrodite/modeling/models/olmoe.py

@@ -19,7 +19,6 @@ from transformers import PretrainedConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.fused_moe import FusedMoE
 from aphrodite.modeling.layers.layernorm import RMSNorm

aphrodite/modeling/models/opt.py

@@ -26,7 +26,6 @@ from transformers import OPTConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import get_act_fn
 from aphrodite.modeling.layers.linear import (ColumnParallelLinear,

aphrodite/modeling/models/orion.py

@@ -13,7 +13,6 @@ from transformers import PretrainedConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import SiluAndMul
 from aphrodite.modeling.layers.linear import (MergedColumnParallelLinear,

aphrodite/modeling/models/paligemma.py

@@ -9,7 +9,6 @@ from transformers import PaliGemmaConfig
 from aphrodite.attention import AttentionMetadata
 from aphrodite.common.config import CacheConfig, MultiModalConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.inputs import INPUT_REGISTRY, InputContext, LLMInputs
 from aphrodite.modeling.layers.logits_processor import LogitsProcessor
 from aphrodite.modeling.layers.sampler import Sampler

aphrodite/modeling/models/persimmon.py

@@ -31,7 +31,6 @@ from transformers.activations import ReLUSquaredActivation
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.linear import (ColumnParallelLinear,
                                               QKVParallelLinear,

aphrodite/modeling/models/phi.py

@@ -44,7 +44,6 @@ from transformers import PhiConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, LoRAConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import get_act_fn
 from aphrodite.modeling.layers.linear import (ColumnParallelLinear,

aphrodite/modeling/models/phi3_small.py

@@ -8,7 +8,6 @@ from transformers.configuration_utils import PretrainedConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, LoRAConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import (get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size)
 from aphrodite.modeling.layers.linear import (MergedColumnParallelLinear,

aphrodite/modeling/models/phi3v.py

@@ -29,7 +29,6 @@ from transformers import CLIPVisionConfig, PretrainedConfig
 from aphrodite.attention import AttentionMetadata
 from aphrodite.common.config import CacheConfig, ModelConfig, MultiModalConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.inputs import INPUT_REGISTRY, InputContext, LLMInputs
 from aphrodite.modeling.layers.logits_processor import LogitsProcessor
 from aphrodite.modeling.layers.sampler import Sampler

aphrodite/modeling/models/qwen.py

@@ -13,7 +13,6 @@ from transformers import PretrainedConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import SiluAndMul
 from aphrodite.modeling.layers.layernorm import RMSNorm

aphrodite/modeling/models/qwen2_moe.py

@@ -32,7 +32,7 @@ from transformers import PretrainedConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import print_warning_once, progress_bar
+from aphrodite.common.utils import print_warning_once
 from aphrodite.distributed import (get_pp_group,
                                    get_tensor_model_parallel_world_size,
                                    tensor_model_parallel_all_reduce)

aphrodite/modeling/models/siglip.py

@@ -14,7 +14,6 @@ from xformers.ops import memory_efficient_attention
 
 from aphrodite.common.config import ModelConfig
 from aphrodite.common.sequence import SequenceData
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.inputs import LLMInputs
 from aphrodite.modeling.layers.activation import get_act_fn

aphrodite/modeling/models/solar.py

@@ -30,7 +30,7 @@ from torch import nn
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, LoRAConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import is_hip, progress_bar
+from aphrodite.common.utils import is_hip
 from aphrodite.distributed import (get_pp_group,
                                    get_tensor_model_parallel_rank,
                                    get_tensor_model_parallel_world_size)

aphrodite/modeling/models/stablelm.py

@@ -28,7 +28,6 @@ from transformers import PretrainedConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import SiluAndMul
 from aphrodite.modeling.layers.linear import (MergedColumnParallelLinear,

aphrodite/modeling/models/starcoder2.py

@@ -27,7 +27,6 @@ from transformers import Starcoder2Config
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import get_act_fn
 from aphrodite.modeling.layers.linear import (ColumnParallelLinear,

aphrodite/modeling/models/xverse.py

@@ -29,7 +29,6 @@ from transformers import PretrainedConfig
 from aphrodite.attention import Attention, AttentionMetadata
 from aphrodite.common.config import CacheConfig, LoRAConfig
 from aphrodite.common.sequence import IntermediateTensors, SamplerOutput
-from aphrodite.common.utils import progress_bar
 from aphrodite.distributed import get_tensor_model_parallel_world_size
 from aphrodite.modeling.layers.activation import SiluAndMul
 from aphrodite.modeling.layers.layernorm import RMSNorm