Remote Tensorflow Execution (rtf): gRPC server and clients generators
Project description
# Remote Tensorflow Execution (RTF)
Bring the power of the Tensorflow Python API to any language, using gRPC.
This repository contains the code of the RTF server and client generator.
**WARNING**: experimental, unstable, WIP.
## Server
The gRPC server implements the server-side protocol. It accepts the requests of function definitions and executes them.
The execution is left to the Python interpreter and the output is streamed back to the client.
### Usage
The server waits for messages and sends back the responses.
#### Requirements
Compile the proto definition is required, however the `setup.py` script takes care of everything. There are 2 options
1. `pip install -e .` to work in edit mode, with the compiled protobufs
2. `pip install .` to install the package (it compiles the proto too)
3. (future) `pip install rtf` | `pip install rtf-gpu`
#### 1. Start the gRPC server
```
python -m rtf.server
```
## Client stub generation
To generate the stub of a client in `DEST_DIR` use the `rtf.generate` module.
```
python -m rtf.generate --dest_dir DEST_DIR --module tensorflow --target Go
```
Right now the only generator that is going to be developed is Go.
Bring the power of the Tensorflow Python API to any language, using gRPC.
This repository contains the code of the RTF server and client generator.
**WARNING**: experimental, unstable, WIP.
## Server
The gRPC server implements the server-side protocol. It accepts the requests of function definitions and executes them.
The execution is left to the Python interpreter and the output is streamed back to the client.
### Usage
The server waits for messages and sends back the responses.
#### Requirements
Compile the proto definition is required, however the `setup.py` script takes care of everything. There are 2 options
1. `pip install -e .` to work in edit mode, with the compiled protobufs
2. `pip install .` to install the package (it compiles the proto too)
3. (future) `pip install rtf` | `pip install rtf-gpu`
#### 1. Start the gRPC server
```
python -m rtf.server
```
## Client stub generation
To generate the stub of a client in `DEST_DIR` use the `rtf.generate` module.
```
python -m rtf.generate --dest_dir DEST_DIR --module tensorflow --target Go
```
Right now the only generator that is going to be developed is Go.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
rtf-0.0.1-py3-none-any.whl
(14.5 kB
view details)
File details
Details for the file rtf-0.0.1-py3-none-any.whl
.
File metadata
- Download URL: rtf-0.0.1-py3-none-any.whl
- Upload date:
- Size: 14.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: Python-urllib/3.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 77b5665257de104cd876a3925d53841c5635fda0e306470db5af5de03672c927 |
|
MD5 | 87fd0133467f1c32c7eee6578d27dde6 |
|
BLAKE2b-256 | 21466b135f544752c75d1bbcfb4021c1015295873402706f8dda682896a1fd46 |