[Lint] Add `python/sglang` to ruff F401 checks and remove unused imports in files (#11685)

python/sglang/test/attention/test_flashattn_mla_backend.py

@@ -4,7 +4,6 @@ import torch
 
 from sglang.srt.configs.model_config import AttentionArch
 from sglang.srt.layers.attention.flashattention_backend import FlashAttentionBackend
-from sglang.srt.layers.attention.torch_native_backend import TorchNativeAttnBackend
 from sglang.srt.layers.radix_attention import RadixAttention
 from sglang.srt.mem_cache.memory_pool import MLATokenToKVPool
 from sglang.srt.model_executor.forward_batch_info import ForwardBatch, ForwardMode

python/sglang/test/attention/test_prefix_chunk_info.py

@@ -2,8 +2,6 @@ import unittest
 
 import torch
 
-from sglang.srt.layers.attention.flashattention_backend import FlashAttentionBackend
-from sglang.srt.layers.radix_attention import RadixAttention
 from sglang.srt.mem_cache.memory_pool import MLATokenToKVPool
 from sglang.srt.model_executor.forward_batch_info import ForwardBatch, ForwardMode
 from sglang.test.test_utils import CustomTestCase

python/sglang/test/few_shot_gsm8k_engine.py

 import argparse
 import ast
 import asyncio
-import json
 import re
 import time
 
 import numpy as np
 
 import sglang as sgl
-from sglang.lang.api import set_default_backend
-from sglang.lang.backend.runtime_endpoint import RuntimeEndpoint
-from sglang.utils import download_and_cache_file, dump_state_text, read_jsonl
+from sglang.utils import download_and_cache_file, read_jsonl
 
 INVALID = -9999999
 

python/sglang/test/simple_eval_gpqa.py

@@ -18,7 +18,6 @@ from sglang.test.simple_eval_common import (
     HTML_JINJA,
     Eval,
     EvalResult,
-    MessageList,
     SamplerBase,
     SingleEvalResult,
     format_multichoice_question,

python/sglang/test/simple_eval_humaneval.py

@@ -11,8 +11,6 @@ import re
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from typing import Dict, List, Optional
 
-import tqdm
-
 try:
     from human_eval.data import read_problems
     from human_eval.evaluation import estimate_pass_at_k
@@ -41,7 +39,6 @@ def evaluate_functional_correctness(
     Evaluates the functional correctness of generated samples, and writes
     results to f"{sample_file}_results.jsonl.gz"
     """
-    import copy
 
     # Check the generated samples against test suites.
     with ThreadPoolExecutor(max_workers=n_workers) as executor:

python/sglang/test/test_block_fp8.py

 import itertools
-import os
 import unittest
 
 import torch
@@ -577,7 +576,7 @@ class TestW8A8BlockFP8BatchedDeepGemm(CustomTestCase):
         if not torch.cuda.is_available():
             raise unittest.SkipTest("CUDA is not available")
         try:
-            import deep_gemm
+            import deep_gemm  # noqa: F401
         except ImportError:
             raise unittest.SkipTest("DeepGEMM is not available")
         torch.set_default_device("cuda")

python/sglang/test/test_block_fp8_deep_gemm_blackwell.py

 import itertools
-import os
 import unittest
 from typing import List, Tuple
 

python/sglang/test/test_cutlass_moe.py

 import argparse
-import time
 
 import torch
 import triton  # Added import

python/sglang/test/test_cutlass_w4a8_moe.py

 # SPDX-License-Identifier: Apache-2.0
 
-from typing import Literal, Optional
+from typing import Optional
 
 import pytest
 import torch

python/sglang/test/test_marlin_moe.py

-import types
 from typing import Optional
 
 import pytest