Files
predict-otron-9001/crates/gemma-runner/Cargo.toml
geoffsee 315ef17605 supports small llama and gemma models
Refactor inference

dedicated crates for llama and gemma inferencing, not integrated
2025-08-29 20:00:41 -04:00

29 lines
1.0 KiB
TOML

[package]
name = "gemma-runner"
version = "0.1.0"
edition = "2021"
[dependencies]
candle-core = { git = "https://github.com/huggingface/candle.git" }
candle-nn = { git = "https://github.com/huggingface/candle.git" }
candle-transformers = { git = "https://github.com/huggingface/candle.git" }
candle-examples = { git = "https://github.com/huggingface/candle.git" }
[target.'cfg(target_os = "macos")'.dependencies]
candle-core = { git = "https://github.com/huggingface/candle.git", features = ["metal"] }
candle-nn = { git = "https://github.com/huggingface/candle.git", features = ["metal"] }
candle-transformers = { git = "https://github.com/huggingface/candle.git", features = ["metal"] }
hf-hub = "0.4"
tokenizers = "0.21"
anyhow = "1.0"
clap = { version = "4.0", features = ["derive", "string"] }
serde_json = "1.0"
tracing = "0.1"
tracing-chrome = "0.7"
tracing-subscriber = "0.3"
[features]
default = []
cuda = ["candle-core/cuda", "candle-nn/cuda", "candle-transformers/cuda"]
metal = ["candle-core/metal", "candle-nn/metal", "candle-transformers/metal"]