Cargo.toml

[package]
name = "ruvllm-wasm"
version = "2.0.0"
edition = "2021"
rust-version = "1.77"
license = "MIT"
authors = ["Ruvector Team"]
repository = "https://github.com/ruvnet/ruvector"
description = "WASM bindings for RuvLLM - browser-compatible LLM inference runtime with WebGPU acceleration"
keywords = ["wasm", "llm", "inference", "browser", "webgpu"]
categories = ["wasm", "api-bindings", "web-programming"]

[package.metadata.wasm-pack.profile.release]
wasm-opt = false

[lib]
crate-type = ["cdylib", "rlib"]

[dependencies]
# WASM bindings
wasm-bindgen = "0.2"
wasm-bindgen-futures = "0.4"
js-sys = "0.3"
# Core web-sys features (always needed)
web-sys = { version = "0.3", features = [
    "console",
    "Performance",
    "Window",
    "Navigator",
    "Worker",
    "WorkerOptions",
    "WorkerType",
    "Blob",
    "BlobPropertyBag",
    "Url",
    "MessageEvent",
    "ErrorEvent",
    "DedicatedWorkerGlobalScope",
] }

# Serialization
serde = { version = "1.0", features = ["derive"] }
serde-wasm-bindgen = "0.6"
serde_json = "1.0"

# Error handling
console_error_panic_hook = { version = "0.1", optional = true }


[dev-dependencies]
wasm-bindgen-test = "0.3"

[features]
default = ["console_error_panic_hook"]
# WebGPU acceleration (adds GPU compute pipeline, shader compilation, buffer management)
webgpu = ["web-sys/Gpu", "web-sys/GpuAdapter", "web-sys/GpuAdapterInfo",
    "web-sys/GpuDevice", "web-sys/GpuQueue", "web-sys/GpuBuffer",
    "web-sys/GpuBufferDescriptor", "web-sys/GpuShaderModule",
    "web-sys/GpuShaderModuleDescriptor", "web-sys/GpuBindGroup",
    "web-sys/GpuBindGroupDescriptor", "web-sys/GpuBindGroupEntry",
    "web-sys/GpuBindGroupLayout", "web-sys/GpuBindGroupLayoutDescriptor",
    "web-sys/GpuBindGroupLayoutEntry", "web-sys/GpuBufferBinding",
    "web-sys/GpuBufferBindingLayout", "web-sys/GpuBufferBindingType",
    "web-sys/GpuComputePipeline", "web-sys/GpuComputePipelineDescriptor",
    "web-sys/GpuPipelineLayout", "web-sys/GpuPipelineLayoutDescriptor",
    "web-sys/GpuProgrammableStage", "web-sys/GpuCommandEncoder",
    "web-sys/GpuCommandEncoderDescriptor", "web-sys/GpuCommandBuffer",
    "web-sys/GpuComputePassEncoder", "web-sys/GpuComputePassDescriptor",
    "web-sys/GpuRequestAdapterOptions", "web-sys/GpuDeviceDescriptor"]
# Enable parallel inference with Web Workers
parallel = []
# Enable SIMD optimizations (requires wasm-simd target feature)
simd = []
# Enable intelligent features (HNSW Router, MicroLoRA, SONA)
intelligent = []
# Enable Pi-Quantization for ultra-low-bit weight compression (ADR-090 Phase 4)
pi-quant = []
# Enable Quantization-Aware Training (requires pi-quant)
qat = ["pi-quant"]