diff --git a/vllm/model_executor/layers/fused_moe/fused_moe.py b/vllm/model_executor/layers/fused_moe/fused_moe.py
index 340da32263c1c..e6f9f01ef0f74 100644
--- a/vllm/model_executor/layers/fused_moe/fused_moe.py
+++ b/vllm/model_executor/layers/fused_moe/fused_moe.py
@@ -105,16 +105,18 @@ def fused_moe_kernel(
     num_tokens_post_padded = tl.load(num_tokens_post_padded_ptr)
     if pid_m * BLOCK_SIZE_M >= num_tokens_post_padded:
         return
-    offs_token_id = pid_m * BLOCK_SIZE_M + tl.arange(0, BLOCK_SIZE_M)
+    offs_token_id = pid_m * BLOCK_SIZE_M + tl.arange(0, BLOCK_SIZE_M).to(
+        tl.int64)
     offs_token = tl.load(sorted_token_ids_ptr + offs_token_id)
     token_mask = offs_token < num_valid_tokens
 
-    offs_bn = (pid_n * BLOCK_SIZE_N + tl.arange(0, BLOCK_SIZE_N)) % N
+    offs_bn = (pid_n * BLOCK_SIZE_N +
+               tl.arange(0, BLOCK_SIZE_N).to(tl.int64)) % N
     offs_k = tl.arange(0, BLOCK_SIZE_K)
     a_ptrs = a_ptr + (offs_token[:, None] // top_k * stride_am +
                       offs_k[None, :] * stride_ak)
 
-    off_experts = tl.load(expert_ids_ptr + pid_m)
+    off_experts = tl.load(expert_ids_ptr + pid_m).to(tl.int64)
     b_ptrs = b_ptr + off_experts * stride_be + (offs_k[:, None] * stride_bk +
                                                 offs_bn[None, :] * stride_bn)
     if use_int8_w8a16: