Metadata-Version: 2.4
Name: remoteipy
Version: 0.0.1
Summary: remote python execution for SolveIt dialogs
Home-page: https://github.com/achalpandeyy/remoteipy
Author: achal
Author-email: pandeyachal.ap@gmail.com
License: MIT License
Keywords: nbdev jupyter notebook python
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Natural Language :: English
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: License :: OSI Approved :: MIT License
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: jupyter_client
Provides-Extra: dev
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: license
Dynamic: license-file
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# remoteipy


<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->

If you are not using SolveIt then this is probably not as relevant to
you.

# Usage

## Connecting

``` python
from remoteipy import connect, is_connected, disconnect
```

``` python
client = connect("ssh -p 16067 root@ssh3.vast.ai -L 8080:localhost:8080", py="/venv/main/bin/python")
```

``` bash
> Connected to IPython kernel at root@ssh3.vast.ai:16067
Welcome to vast.ai. If authentication fails, try again after a few seconds, and double check your ssh key.
Have fun!
```

``` python
is_connected(client)
```

    > True

## Running code

``` python
%%remote

import sys
print(sys.version)
```

``` bash
> 3.10.12 (main, Feb  4 2025, 14:57:36) [GCC 11.4.0]
```

``` python
%%remote

!nvidia-smi
```

``` bash
> Wed Dec 10 10:05:54 2025       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 570.172.08             Driver Version: 570.172.08     CUDA Version: 12.8     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA H100 80GB HBM3          On  |   00000000:05:00.0 Off |                  Off |
| N/A   29C    P0             76W /  700W |       0MiB /  81559MiB |      0%      Default |
|                                         |                        |             Disabled |
+-----------------------------------------+------------------------+----------------------+
                                                                                         
+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
|  No running processes found                                                             |
+-----------------------------------------------------------------------------------------+
```

## Asking SolveIt

What GPU am I running? Would you call me GPU-rich or GPU-poor ;)?

> You’re running an NVIDIA H100 80GB HBM3 — that’s the flagship
> datacenter GPU from NVIDIA’s Hopper generation!
>
> I’d definitely call you GPU-rich 🤑 — that’s one of the most powerful
> GPUs available for AI/ML workloads. The H100 80GB is what the big labs
> use for training large models. You’ve got:
>
> - 80GB of ultra-fast HBM3 memory
> - Up to 700W of compute power at your fingertips
> - CUDA 12.8 support
>
> You’re sitting pretty! What are you planning to run on this beast?

## Running more code

``` python
%%remote

import torch

A = torch.ones(4096, 4096, dtype=torch.float32, device="cuda")
A
```

    > tensor([[1., 1., 1.,  ..., 1., 1., 1.],
            [1., 1., 1.,  ..., 1., 1., 1.],
            [1., 1., 1.,  ..., 1., 1., 1.],
            ...,
            [1., 1., 1.,  ..., 1., 1., 1.],
            [1., 1., 1.,  ..., 1., 1., 1.],
            [1., 1., 1.,  ..., 1., 1., 1.]], device='cuda:0')

What did I just do?

> You just created a 4096×4096 matrix filled with ones on your GPU (the
> H100)!
>
> Specifically: - torch.ones() creates a tensor (PyTorch’s version of an
> array) filled with 1s - dtype=torch.float32 means each element is a
> 32-bit floating point number - device=“cuda” puts it on your GPU
> memory instead of CPU RAM This tensor is taking up about 64 MB of your
> GPU’s 80GB memory (4096 × 4096 × 4 bytes per float32).
>
> Are you planning to do some matrix operations or neural network work
> with this?You just created a 4096×4096 matrix filled with ones on your
> GPU! Specifically, you:
>
> Created a PyTorch tensor with 32-bit floating point values Allocated
> it directly on the CUDA device (your H100 GPU) The tensor contains
> about 16.8 million elements (all set to 1.0) This takes up about 64 MB
> of your GPU’s 80 GB memory. Are you planning to do some matrix
> operations or neural network work with it?

## Disconnecting

``` python
disconnect(client)
```

``` bash
> Exit requrest sent.
```

``` python
is_connected(client)
```

``` bash
> False
```

### Installation

Install latest from the GitHub
[repository](https://github.com/achalpandeyy/remoteipy):

``` sh
$ pip install git+https://github.com/achalpandeyy/remoteipy.git
```

``` sh
$ pip install remoteipy
```

### Documentation

Documentation can be found hosted on this GitHub
[repository](https://github.com/achalpandeyy/remoteipy)’s
[pages](https://achalpandeyy.github.io/remoteipy/). Additionally you can
find package manager specific guidelines on
[pypi](https://pypi.org/project/remoteipy/).
