Files

71 lines
1.6 KiB
TOML

[package]
name = "ruvllm-cli"
version.workspace = true
edition.workspace = true
rust-version.workspace = true
license.workspace = true
authors.workspace = true
repository.workspace = true
description = "CLI for RuvLLM model management and inference on Apple Silicon"
[[bin]]
name = "ruvllm"
path = "src/main.rs"
[dependencies]
# RuvLLM core library
ruvllm = { path = "../ruvllm", features = ["candle"] }
# CLI framework
clap = { version = "4.5", features = ["derive", "cargo", "env"] }
indicatif = { workspace = true }
console = { workspace = true }
# Async runtime
tokio = { workspace = true, features = ["full", "signal"] }
futures = { workspace = true }
# HuggingFace Hub for model downloads
hf-hub = { version = "0.3", features = ["tokio"] }
# HTTP server for inference API
axum = { version = "0.7", features = ["ws"] }
tower = "0.5"
tower-http = { version = "0.6", features = ["cors", "trace"] }
# Serialization
serde = { workspace = true }
serde_json = { workspace = true }
# Error handling
thiserror = { workspace = true }
anyhow = { workspace = true }
tracing = { workspace = true }
tracing-subscriber = { workspace = true }
# Utilities
chrono = { workspace = true }
uuid = { workspace = true }
dirs = "5.0"
colored = "2.1"
rustyline = "14.0"
ctrlc = "3.4"
bytesize = "1.3"
prettytable-rs = "0.10"
dialoguer = "0.11"
# Streaming
async-stream = "0.3"
[dev-dependencies]
assert_cmd = "2.0"
predicates = "3.1"
tempfile = "3.13"
[features]
default = []
# Metal acceleration for Apple Silicon (M1/M2/M3/M4)
metal = ["ruvllm/metal"]
# CUDA acceleration for NVIDIA GPUs
cuda = ["ruvllm/cuda"]