synor/sdk/kotlin

Synor Compute SDK for Kotlin

Access distributed heterogeneous compute at 90% cost reduction.

Installation

Gradle (Kotlin DSL)

implementation("io.synor:compute-sdk-kotlin:0.1.0")

Gradle (Groovy)

implementation 'io.synor:compute-sdk-kotlin:0.1.0'

Quick Start

import io.synor.compute.*
import kotlinx.coroutines.runBlocking

fun main() = runBlocking {
    val client = SynorCompute("your-api-key")

    // Matrix multiplication on GPU
    val a = Tensor.random(512, 512)
    val b = Tensor.random(512, 512)

    val result = client.matmul(a, b) {
        precision = Precision.FP16
        processor = ProcessorType.GPU
    }

    if (result.isSuccess) {
        println("Time: ${result.executionTimeMs}ms")
        println("Cost: $${result.cost}")
    }
}

Kotlin Coroutines Support

// Suspend functions
suspend fun compute() {
    val result = client.matmul(a, b)
    println(result.result)
}

// Flows for streaming
client.inferenceStream("llama-3-70b", "Write a poem")
    .collect { chunk ->
        print(chunk)
    }

Tensor Operations

// Create tensors
val zeros = Tensor.zeros(3, 3)
val ones = Tensor.ones(2, 2)
val random = Tensor.random(10, 10)
val randn = Tensor.randn(100)
val eye = Tensor.eye(3)

// From array
val data = arrayOf(
    floatArrayOf(1f, 2f, 3f),
    floatArrayOf(4f, 5f, 6f)
)
val tensor = Tensor.from(data)

// Operations
val reshaped = tensor.reshape(3, 2)
val transposed = tensor.transpose()

// Math (extension properties)
val mean = tensor.mean
val sum = tensor.sum
val std = tensor.std

DSL-Style API

// Matrix multiplication with DSL
val result = client.matmul(a, b) {
    precision = Precision.FP16
    processor = ProcessorType.GPU
    priority = Priority.HIGH
    strategy = BalancingStrategy.SPEED
}

// Convolution
val conv = client.conv2d(input, kernel) {
    stride = 1 to 1
    padding = 1 to 1
}

// Attention
val attention = client.attention(query, key, value) {
    numHeads = 8
    flash = true
}

LLM Inference

// Single response
val response = client.inference("llama-3-70b", "Explain quantum computing") {
    maxTokens = 512
    temperature = 0.7
}
println(response.result)

// Streaming with Flow
client.inferenceStream("llama-3-70b", "Write a poem")
    .collect { chunk ->
        print(chunk)
    }

Configuration

val config = SynorConfig(
    apiKey = "your-api-key",
    baseUrl = "https://api.synor.io/compute/v1",
    defaultProcessor = ProcessorType.GPU,
    defaultPrecision = Precision.FP16,
    timeout = 30.seconds,
    debug = true
)

val client = SynorCompute(config)

Error Handling

try {
    val result = client.matmul(a, b)
} catch (e: SynorException) {
    println("API Error: ${e.message} (${e.statusCode})")
}

// Or with Result type
val result = runCatching {
    client.matmul(a, b)
}

result.onSuccess { println("Success: ${it.result}") }
       .onFailure { println("Failed: ${it.message}") }

Extension Functions

// Operator overloading
val c = a * b  // Matrix multiplication
val d = a + b  // Element-wise addition

// Infix functions
val result = a matmul b

Types

// Sealed classes for type safety
sealed class ProcessorType {
    object Cpu : ProcessorType()
    object Gpu : ProcessorType()
    object Tpu : ProcessorType()
    object Auto : ProcessorType()
}

enum class Precision {
    FP64, FP32, FP16, BF16, INT8, INT4
}

enum class JobStatus {
    PENDING, RUNNING, COMPLETED, FAILED, CANCELLED
}

Requirements

• Kotlin 1.9+
• Kotlinx Coroutines
• Kotlinx Serialization

Testing

./gradlew test

License

MIT