Neural network inference the Unix way.
cloudkj/layer is ranked 16,994 with 561 stars.
Same-category comparison
cloudkj/layer is ranked 16,994 among these 8 peers; Dstack-TEE/dstack is ranked 16,988.
Same-category comparison| Name | Rank | Metrics |
|---|
| jaylfc/taOS | 16,964 | - Language:
- Python
- Stars:
- 563
- Forks:
- 43
- Description:
- Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memory (taOSmd), self-hosted multi-framework group chat, a full web desktop + app store, and auto-clustering across the consumer hardware you already have (Orange/Raspberry Pi, Mac mini, gaming PC).
|
|---|
| labring/aiproxy | 16,965 | - Language:
- Go
- Stars:
- 563
- Forks:
- 116
- Description:
- AI Proxy is a high performance AI gateway using OpenAI / Claude / Gemini protocol as the entry point. It features intelligent error handling, multi-channel management, and comprehensive monitoring. With support for multiple models, rate limiting, and multi-tenant isolation.
|
|---|
| facebookresearch/HolisticTraceAnalysis | 16,976 | - Language:
- Python
- Stars:
- 562
- Forks:
- 98
- Description:
- A library to analyze PyTorch traces.
|
|---|
| Dstack-TEE/dstack | 16,988 | - Language:
- Rust
- Stars:
- 561
- Forks:
- 99
- Description:
- Open framework for confidential AI.
|
|---|
| kelindar/search | 17,000 | - Language:
- Go
- Stars:
- 561
- Forks:
- 24
- Description:
- Go library for embedded vector search and semantic embeddings using llama.cpp.
|
|---|
| llumnix-project/llumnix-ray | 17,003 | - Language:
- Python
- Stars:
- 561
- Forks:
- 50
- Description:
- Efficient and easy multi-instance LLM serving.
|
|---|
| maxbbraun/llama4micro | 17,005 | - Language:
- C++
- Stars:
- 561
- Forks:
- 37
- Description:
- A "large" language model running on a microcontroller.
|
|---|
| zengxiao-he/tessera | 17,012 | - Language:
- Python
- Stars:
- 561
- Forks:
- 10
|
|---|
Key parameters and specifications
Key parameters and specifications| Parameter | Value |
|---|
| Language | Scheme |
|---|
| Category | Infrastructure |
|---|
| Subcategory | Inference service optimization |
|---|
| Stars | 561 |
|---|
| Forks | 18 |
|---|
| Contributors | 1 |
|---|
| Created date | 2018-12-08 |
|---|
| Updated date | 2026-10-13 |
|---|
| Stars in 1 day | 0 |
|---|
| Stars in 7 days | 1 |
|---|
| Rank | 16,994 |
|---|
| Previous rank | 16,783 |
|---|
| Rank change | -211 |
|---|
| 7-day stars rank | 11,340 |
|---|
| Previous 7-day stars rank | 11,401 |
|---|
| 7-day stars rank change | 61 |
|---|
| Total stars rank | 17,697 |
|---|
| Previous total stars rank | 17,664 |
|---|
| Total stars rank change | -33 |
|---|
| Country | USA |
|---|
README summary
layer - neural network inference from the command line is a program for doing neural network inference the Unix way. Many modern neural network operations can be represented as sequential, unidirectional streams of data processed by pipelines of filters). The computations at each layer in these neural networks are equivalent to an invocation of the program, and multiple invocations can be chained together to represent the entirety of such networks. For example, performing inference on a neural network with two fully
-connected layers might look something like this: applies the Unix philosophy to neural network inference. Each type of a neural network layer is a distinct subcommand. Simple text streams of delimited numeric values serve as the interface between different layers of a neural network. Each invocation of does one thing: it feeds the numeric input values forward through an instantiation of a neural network layer, then emits the resulting output numeric values. Usage Example: a convolutional neural network for CIFAR
-10. Example: a multi-layer perceptron for XOR. 0+ On Debian-based systems: On RPM-based system: On macOS 10. 3+, BLAS is pre-installed as part of the 3. Unzip the release and run , or manually relocate the binaries to the path of your choice. About is currently implemented as a proof-of-concept and supports a limited number of neural network layer types. The types of layers are currently limited to feed-forward layers that can be modeled
as sequential, unidirectional pipelines. Input values, weights and biases for parameterized layers, and output values are all read and written in row-major order, based on the shape parameters specified for each layer.
Frequently asked questions
How many stars and forks are recorded?
cloudkj/layer has 561 stars and 18 forks.
What is the repository rank?
cloudkj/layer is ranked 16,994.
What language and category are recorded?
cloudkj/layer has 561 stars, uses Scheme and belongs to Infrastructure.
Which repository is closest in rank?
cloudkj/layer is compared with Dstack-TEE/dstack, ranked 16,988 with 561 stars.
layer - neural network inference from the command line
layer is a program for doing neural network inference the Unix way. Many
modern neural network operations can be represented as sequential,
unidirectional streams of data processed by pipelines of filters.
The computations at each layer in these neural networks are equivalent to an
invocation of the layer program, and multiple invocations can be chained
together to represent the entirety of such networks.
For example, performing inference on a neural network with two fully-connected
layers might look something like this:
cat input | layer full -w w.1 --input-shape=2 -f tanh | layer full -w w.2 --input-shape=3 -f sigmoid
layer applies the Unix philosophy to neural network inference. Each type of
a neural network layer is a distinct subcommand. Simple text streams of
delimited numeric values serve as the interface between different layers of a
neural network. Each invocation of layer does one thing: it feeds the numeric
input values forward through an instantiation of a neural network layer, then
emits the resulting output numeric values.
Usage
Example: a convolutional neural network for CIFAR-10.
$ cat cifar10_x.csv \
| layer convolutional -w w0.csv -b b0.csv --input-shape=32,32,3 --filter-shape=3,3 --num-filters=32 -f relu \
| layer convolutional -w w1.csv -b b1.csv --input-shape=30,30,32 --filter-shape=3,3 --num-filters=32 -f relu \
| layer pooling --input-shape=28,28,32 --filter-shape=2,2 --stride=2 -f max
Example: a multi-layer perceptron for XOR.
$ # Fully connected layer with three neurons
echo "-2.35546875,-2.38671875,3.63671875,3.521484375,-2.255859375,-2.732421875" > layer1.weights
echo "0.7958984375,0.291259765625,1.099609375" > layer1.biases
$ # Fully connected layer with one neuron
echo "-5.0625,-3.515625,-5.0625" > layer2.weights
echo "1.74609375" > layer2.biases
$ # Compute XOR for all possible binary inputs
echo -e "0,0\n0,1\n1,0\n1,1" \
| layer full -w layer1.weights -b layer1.biases --input-shape=2 -f tanh \
| layer full -w layer2.weights -b layer2.biases --input-shape=3 -f sigmoid
0.00129012749948779
0.99147053740106
0.991243357927591
0.0111237568184365
Installation
Requirements: BLAS 3.6.0+
- Download a release
- Install BLAS 3.6.0+
- On Debian-based systems:
apt-get install -y libblas3
- On RPM-based system:
yum install -y blas
- On macOS 10.3+, BLAS is pre-installed as part of the
Accelerate framework
- Unzip the release and run
[sudo] ./install.sh, or manually relocate the
binaries to the path of your choice.
About
layer is currently implemented as a proof-of-concept and supports a limited
number of neural network layer types. The types of layers are currently limited
to feed-forward layers that can be modeled as sequential, unidirectional
pipelines.
Input values, weights and biases for parameterized layers, and output values
are all read and written in row-major order,
based on the shape parameters specified for each layer.
layer is implemented in CHICKEN Scheme.
License
Copyright © 2018-2019