[CI] update typos config for CI pre-commit and fix some spells (#20919)

Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>

csrc/cpu/sgl-kernels/common.h

@@ -58,7 +58,7 @@ namespace {
 
 #define CHECK_CONTIGUOUS(x) TORCH_CHECK(x.is_contiguous(), #x " must be contiguous")
 #define CHECK_LAST_DIM_CONTIGUOUS(x) \
-  TORCH_CHECK(x.strides()[x.strides().size() - 1] == 1, #x "must be contiguous at last dimention")
+  TORCH_CHECK(x.strides()[x.strides().size() - 1] == 1, #x "must be contiguous at last dimension")
 
 #define CHECK_INPUT(x) \
   CHECK_CPU(x);        \

csrc/cpu/sgl-kernels/gemm.h

@@ -126,7 +126,7 @@ void fused_experts_int4_w4a16_kernel_impl(
     int64_t topk,
     int64_t num_tokens_post_pad);
 
-// shared expert implememntation for int8 w8a8
+// shared expert implementation for int8 w8a8
 template <typename scalar_t>
 void shared_expert_int8_kernel_impl(
     scalar_t* __restrict__ output,

csrc/cpu/sgl-kernels/gemm_int8.cpp

@@ -41,7 +41,7 @@ struct tinygemm_kernel_nn<at::BFloat16, has_bias, BLOCK_M, BLOCK_N> {
     __m512  vd0;
     __m512  vd1[COLS];
 
-    // oops! 4x4 spills but luckly we use 4x2
+    // oops! 4x4 spills but luckily we use 4x2
     __m512 vbias[COLS];
 
     // [NOTE]: s8s8 igemm compensation in avx512-vnni

csrc/cpu/sgl-kernels/vec.h

@@ -37,7 +37,7 @@ inline Vectorized<at::BFloat16> convert_from_float_ext<at::BFloat16>(const Vecto
 #define CVT_FP16_TO_FP32(a) \
     _mm512_cvtps_ph(a, (_MM_FROUND_TO_NEAREST_INT | _MM_FROUND_NO_EXC))
 
-// this doesn't hanel NaN.
+// this doesn't handle NaN.
 inline __m512bh cvt_e4m3_bf16_intrinsic_no_nan(__m256i fp8_vec) {
   const __m512i x = _mm512_cvtepu8_epi16(fp8_vec);