Fix a bug in BatchTokenIDOut & Misc style and dependency updates (#7457)

sgl-kernel/CMakeLists.txt

@@ -39,14 +39,6 @@ find_package(Torch REQUIRED)
 # clean Torch Flag
 clear_cuda_arches(CMAKE_FLAG)
 
-if("${CUDA_VERSION}" VERSION_EQUAL "12.8")
-  set(DeepGEMM_REPO "https://github.com/sgl-project/DeepGEMM")
-  set(DeepGEMM_TAG "blackwell")
-else()
-  set(DeepGEMM_REPO "https://github.com/deepseek-ai/DeepGEMM")
-  set(DeepGEMM_TAG "8dfa3298274bfe6b242f6f8a3e6f3eff2707dd9f")
-endif()
-
 include(FetchContent)
 
 # cutlass
@@ -57,7 +49,16 @@ FetchContent_Declare(
     GIT_SHALLOW    OFF
 )
 FetchContent_Populate(repo-cutlass)
+
 # DeepGEMM
+if("${CUDA_VERSION}" VERSION_EQUAL "12.8")
+  set(DeepGEMM_REPO "https://github.com/sgl-project/DeepGEMM")
+  set(DeepGEMM_TAG "blackwell")
+else()
+  set(DeepGEMM_REPO "https://github.com/deepseek-ai/DeepGEMM")
+  set(DeepGEMM_TAG "8dfa3298274bfe6b242f6f8a3e6f3eff2707dd9f")
+endif()
+
 FetchContent_Declare(
     repo-deepgemm
     GIT_REPOSITORY ${DeepGEMM_REPO}
@@ -107,7 +108,6 @@ if (CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64")
     message(STATUS "For aarch64, disable gencode below SM90 by default")
 endif()
 
-
 include_directories(
     ${PROJECT_SOURCE_DIR}/include
     ${PROJECT_SOURCE_DIR}/csrc
@@ -247,8 +247,8 @@ set(SOURCES
     "csrc/moe/ep_moe_reorder_kernel.cu"
     "csrc/moe/ep_moe_silu_and_mul_kernel.cu"
     "csrc/speculative/eagle_utils.cu"
-    "csrc/speculative/speculative_sampling.cu"
     "csrc/speculative/packbit.cu"
+    "csrc/speculative/speculative_sampling.cu"
     "csrc/grammar/apply_token_bitmask_inplace_cuda.cu"
     "csrc/common_extension.cc"
     "${repo-flashinfer_SOURCE_DIR}/csrc/norm.cu"

sgl-kernel/python/sgl_kernel/sampling.py

@@ -1,7 +1,7 @@
 from typing import Optional, Union
 
 import torch
-from sgl_kernel.utils import _to_tensor_scalar_tuple, get_cuda_stream
+from sgl_kernel.utils import _to_tensor_scalar_tuple
 
 
 def _top_k_renorm_probs_internal(