[package]
name = "rmistral"
version = "0.1.0"
edition = "2021"
description = "A simple interface for Mistral models "
license = "MIT/Apache-2.0"
repository = "https://github.com/floneum/floneum"
authors = ["Evan Almloff"]

# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

[dependencies]
candle-core.workspace = true
candle-nn.workspace = true
candle-transformers.workspace = true
tokenizers = { version = "0.13.4" }
hf-hub = "0.3.0"

accelerate-src = { version = "0.3.2", optional = true }
intel-mkl-src = { version = "0.8.1", features = ["mkl-static-lp64-iomp"], optional = true }
cudarc = { version = "0.9.14", features = ["f16"], optional = true }
half = { version = "2.3.1", features = ["num-traits", "use-intrinsics", "rand_distr"], optional = true }

anyhow = "1.0.75"
tracing = "0.1.37"
serde_json = "1.0.106"
rand = "0.8.5"
tokio = { version = "1.32.0", features = ["full"] }
async-trait = "0.1.73"
llm-samplers = { workspace = true }
kalosm-sample.workspace = true
kalosm-language-model.workspace = true
kalosm-streams.workspace = true

[features]
accelerate = ["dep:accelerate-src", "candle-core/accelerate", "candle-nn/accelerate", "candle-transformers/accelerate"]
cuda = ["candle-core/cuda", "candle-nn/cuda", "candle-transformers/cuda"]
cudnn = ["candle-core/cudnn"]
mkl = ["dep:intel-mkl-src", "candle-core/mkl", "candle-nn/mkl", "candle-transformers/mkl"]
nccl = ["cuda", "cudarc/nccl", "dep:half"]