Update deep_ep.cpp

csrc/deep_ep.cpp

@@ -614,6 +614,8 @@ Buffer::internode_dispatch(const torch::Tensor& x, const std::optional<torch::Te
                            const std::optional<torch::Tensor>& cached_rdma_channel_prefix_matrix, const std::optional<torch::Tensor>& cached_recv_rdma_rank_prefix_sum,
                            const std::optional<torch::Tensor>& cached_gbl_channel_prefix_matrix, const std::optional<torch::Tensor>& cached_recv_gbl_rank_prefix_sum,
                            int expert_alignment, const Config& config, std::optional<EventHandle>& previous_event, bool async, bool allocate_on_comm_stream) {
+    pybind11::gil_scoped_release release;
+
     const int num_channels = config.num_sms / 2;
     EP_HOST_ASSERT(config.num_sms % 2 == 0);
     EP_HOST_ASSERT(0 < get_num_rdma_ranks() and get_num_rdma_ranks() <= NUM_MAX_RDMA_PEERS);