# How to keep the data in GPU memory after remote call?
**URL:** https://discuss.ray.io/t/how-to-keep-the-data-in-gpu-memory-after-remote-call/1287
**Category:** Ray Core
**Created:** [March 17, 2021, 5:49am UTC](https://discuss.ray.io/t/how-to-keep-the-data-in-gpu-memory-after-remote-call/1287 "2021-03-17T05:49:06Z")
**Posts on this page:** 2
**Page:** 1
### Author:  [@zjacob](https://discuss.ray.io/u/zjacob)
#### Post date: [March 17, 2021, 5:49am UTC](https://discuss.ray.io/t/how-to-keep-the-data-in-gpu-memory-after-remote-call/1287/1 "2021-03-17T05:49:06Z")
I have a large data array on GPU memory, and I would like to replace one row of this data while keeping all the other rows unchanged at each call of the remote function. The GPU kernel is a Ray remote function. However, I find that after calling the remote function, the data array will be set zero on GPU memory, and the previously replaced rows will be all zero.
> import ray
> from numba import cuda
> import numpy as np
>
> ray.init(ignore\_reinit\_error=True)
# copy newly calculated ‘new’ to ‘temp’ (on GPU memory) in row ii
> @cuda.jit
> def copy\_(length, new, temp, ii):
>
> ```
> i = cuda.grid(1)
>
> # loop through each spatial grid
> if i < length:
> temp[ii,i] = new[i]
>
> ```
>
> @ray.remote(num\_gpus=1)
> def solver(length, new, ii):
>
> ```
> temp = cuda.device_array([5,length])
> new = cuda.to_device(new)
>
> # Configure the blocks
> threadsperblock = 32
>
> # configure the grids
> blockspergrid = (length + (threadsperblock - 1)) // threadsperblock
>
> copy_[blockspergrid, threadsperblock](length, new, temp, ii)
>
> return temp.copy_to_host()
>
> ```
>
> length = 10
>
> new = np.arange(length)
# specify the index to replace, if next time ii = 1, the copied ii=0 row will be zero
> ii = 0
> re = solver.remote(length, new, ii)
> ray.get(re)
The above code will reset the data array. I want the array ‘temp’ to stay on the GPU memory.
If instead, I feed the data array ‘temp’ as an input in remote function, the data array cannot be pickled.
Is there a way such that this can be done?
---
### Author:  [@Dmitri](https://discuss.ray.io/u/Dmitri)
#### Post date: [March 18, 2021, 2:51am UTC](https://discuss.ray.io/t/how-to-keep-the-data-in-gpu-memory-after-remote-call/1287/2 "2021-03-18T02:51:53Z")
cc @Clark_Zinzow @ericl