diff --git a/src/liger_kernel/ops/llama4_rope.py b/src/liger_kernel/ops/llama4_rope.py
index 9167d69f3..02a8647be 100644
--- a/src/liger_kernel/ops/llama4_rope.py
+++ b/src/liger_kernel/ops/llama4_rope.py
@@ -39,7 +39,7 @@ def _llama4_rope_kernel(
     Grid: (batch*seq, head)
     """
     # 2D grid
-    pid_bs = tl.program_id(0)  # over batch*seq
+    pid_bs = tl.program_id(0).to(tl.int64)  # over batch*seq
     pid_h = tl.program_id(1)  # over heads
 
     batch_idx = pid_bs // seq_len
diff --git a/src/liger_kernel/ops/qwen2vl_mrope.py b/src/liger_kernel/ops/qwen2vl_mrope.py
index fbd120f96..b431c8976 100644
--- a/src/liger_kernel/ops/qwen2vl_mrope.py
+++ b/src/liger_kernel/ops/qwen2vl_mrope.py
@@ -22,7 +22,7 @@ def _triton_qwen2vl_mrope(
     BLOCK_SIZE: tl.constexpr,
     BACKWARD_PASS: tl.constexpr = False,
 ):
-    pid = tl.program_id(0)
+    pid = tl.program_id(0).to(tl.int64)
 
     # locate start address
     q_ptr = q_ptr + pid * (n_qh * hd)