Out of Dynamic GPU memory in EnsembleGPUKernel for higher number of threads when using ContinuousCallback

Hello, I was testing the new updates to Terminete! with EnsembleGPUKernel. It Works fine with DiscreteCallback, however when using ContinuousCallback I still have the problem, Out of Dynamic GPU memory in EnsembleGPUKernel for higher number of threads. I attach the code used

using StaticArrays
using CUDA
using DiffEqGPU
using NPZ
using OrdinaryDiffEq
using Plots

"""
     pot_central(u,p,t)
     u=[x,dx,y,dy]
     p=[k,m]
"""
function pot_central(u,p,t)
      r3 = ( u[1]^2 + u[3]^2 )^(3/2)
     du1 = u[2]                           # u[2]= dx
     du2 =  -( p[1]*u[1] ) / ( p[2]*r3 )    
     du3 = u[4]                           # u[4]= dy
     du4 =  -( p[1]*u[3] ) / ( p[2]*r3 ) 

     return SVector{4}(du1,du2,du3,du4)
end

T = 100.0
 k = 1.0
 m = 1.0
trajectories = 5_000
u_rand = convert(Array{Float64},npzread("IO_GPU/IO_u0.npy"))

    u0 =  @SVector [2.0; 2.0; 1.0; 1.5]
     p =  @SVector [k,m]                      
 tspan =  (0.0,T)   

     prob = ODEProblem{false}(pot_central,u0,tspan,p)
prob_func = (prob,i,repeat) -> remake(prob, u0 = SVector{4}(u_rand[i,:]).*u0 + @SVector [1.0;1.0;1.0;1.0] )
Ensemble_Problem = EnsembleProblem(prob,prob_func=prob_func,safetycopy=false)


function condition(u,t,integrator)
    R2 = @SVector [4.5,5_000.0]                          # R2=[Rmin2,Rmax2]   
    r2 = u[1]*u[1] + u[3]*u[3]
    (R2[2] - r2)*(r2 - R2[1])#< 0.0
end

affect!(integrator) = terminate!(integrator)
gpu_cb =  ContinuousCallback(condition, affect!;save_positions=(false,false),rootfind=true,interp_points=0,abstol=1e-7,reltol=0)
#gpu_cb =  DiscreteCallback(condition, affect!;save_positions=(false,false))

CUDA.@time sol= solve(Ensemble_Problem,
                                GPUTsit5(),
                                #GPUVern7(),
                                #GPUVern9(),
                                EnsembleGPUKernel(),
                                trajectories = trajectories,
                                batch_size = 10_000,
                                adaptive = false,
                                dt = 0.01,
                                save_everystep = false,
                                callback = gpu_cb,
                                merge_callbacks = true
                                )