[CI/Build] drop support for Python 3.8 EOL (#8464)

Signed-off-by: Aaron Pham <contact@aarnphm.xyz>

vllm/transformers_utils/configs/chatglm.py

@@ -1,4 +1,3 @@
-# coding=utf-8
 # Adapted from
 # https://github.com/THUDM/ChatGLM2-6B
 from transformers import PretrainedConfig

vllm/transformers_utils/configs/exaone.py

@@ -1,4 +1,3 @@
-# coding=utf-8
 # Copied from
 # https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct/blob/main/configuration_exaone.py
 # Copyright 2021 The LG AI Research EXAONE Lab. All rights reserved.

vllm/transformers_utils/configs/jais.py

@@ -1,4 +1,3 @@
-# coding=utf-8
 # Copyright 2023 The OpenAI Team Authors and HuggingFace Inc. team.
 # Copyright (c) 2018, NVIDIA CORPORATION.  All rights reserved.
 # Copyright 2023 Cerebras Systems.

vllm/transformers_utils/configs/mpt.py

@@ -1,4 +1,3 @@
-# coding=utf-8
 # Copied from
 # https://huggingface.co/mosaicml/mpt-7b/blob/main/configuration_mpt.py
 """A HuggingFace-style model configuration."""
@@ -117,10 +116,10 @@ class MPTConfig(PretrainedConfig):
                                                      init_config_defaults)
         if self.d_model % self.n_heads != 0:
             raise ValueError('d_model must be divisible by n_heads')
-        if any((
+        if any(
                 prob < 0 or prob > 1 for prob in
-            [self.attn_config['attn_pdrop'], self.resid_pdrop, self.emb_pdrop]
-        )):
+            [self.attn_config['attn_pdrop'], self.resid_pdrop, self.emb_pdrop
+             ]):
             raise ValueError(
                 "self.attn_config['attn_pdrop'], resid_pdrop, emb_pdrop are "
                 "probabilities and must be between 0 and 1")

vllm/transformers_utils/configs/nemotron.py

@@ -1,4 +1,3 @@
-# coding=utf-8
 # Copyright 2024 HuggingFace Inc. team. All rights reserved.
 # Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
 #
@@ -144,7 +143,7 @@ class NemotronConfig(PretrainedConfig):
         self.intermediate_size = intermediate_size
         self.num_hidden_layers = num_hidden_layers
         self.num_attention_heads = num_attention_heads
-        head_dim = head_dim or kwargs.get("kv_channels", None)
+        head_dim = head_dim or kwargs.get("kv_channels")
         self.head_dim = head_dim if head_dim is not None else (
             hidden_size // num_attention_heads)
 
@@ -160,8 +159,8 @@ class NemotronConfig(PretrainedConfig):
         self.rope_theta = rope_theta
         self.rope_scaling = rope_scaling
         # for backward compatibility
-        partial_rotary_factor = kwargs.get("rope_percent", None) or kwargs.get(
-            "rope_percentage", None) or partial_rotary_factor
+        partial_rotary_factor = kwargs.get("rope_percent") or kwargs.get(
+            "rope_percentage") or partial_rotary_factor
         self.partial_rotary_factor = partial_rotary_factor
         self._rope_scaling_validation()
         self.attention_bias = attention_bias

vllm/transformers_utils/configs/solar.py

@@ -1,4 +1,3 @@
-# coding=utf-8
 # Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
 #
 # This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX