[Misc] Fused MoE Marlin support for GPTQ (#8217)

csrc/moe/marlin_moe_ops.cu

@@ -1737,4 +1737,4 @@ torch::Tensor marlin_gemm_moe(
       moe_block_size, dev, at::cuda::getCurrentCUDAStream(dev), thread_k,
       thread_n, sms, max_par, replicate_input, apply_weights);
   return c;
-}
+}

csrc/moe/marlin_moe_ops.h

@@ -9,4 +9,4 @@ torch::Tensor marlin_gemm_moe(
     const torch::Tensor& g_idx, const torch::Tensor& perm,
     torch::Tensor& workspace, int64_t size_m, int64_t size_n, int64_t size_k,
     bool is_k_full, int64_t num_experts, int64_t topk, int64_t moe_block_size,
-    bool replicate_input, bool apply_weights);
+    bool replicate_input, bool apply_weights);

csrc/moe/torch_bindings.cpp

@@ -16,7 +16,6 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, m) {
       "g_idx, Tensor! perm, Tensor! workspace, int size_m, int size_n, int "
       "size_k, bool is_k_full, int num_experts, int topk, int moe_block_size, "
       "bool replicate_input, bool apply_weights) -> Tensor");
-
   m.impl("marlin_gemm_moe", torch::kCUDA, &marlin_gemm_moe);
 #endif
 }