[package]
authors = ["nathanielsimard <nathaniel.simard.42@gmail.com>"]
categories = ["science", "no-std", "embedded", "wasm"]
description = "Tensor library with user-friendly APIs and automatic differentiation support"
edition.workspace = true
keywords = ["deep-learning", "machine-learning", "tensor", "pytorch", "ndarray"]
license.workspace = true
name = "burn-tensor"
readme.workspace = true
repository = "https://github.com/tracel-ai/burn/tree/main/crates/burn-tensor"
version.workspace = true

[features]
default = ["std", "repr"]
doc = ["default"]
experimental-named-tensor = []
export_tests = ["burn-tensor-testgen"]
std = ["rand/std", "half/std", "num-traits/std", "burn-common/std", "burn-common/rayon"]
repr = []
cubecl = ["dep:cubecl"]
cubecl-wgpu = ["cubecl", "cubecl/wgpu"]
cubecl-cuda = ["cubecl", "cubecl/cuda"]

[dependencies]
burn-common = { path = "../burn-common", version = "0.14.0", default-features = false}
burn-tensor-testgen = { path = "../burn-tensor-testgen", version = "0.14.0", optional = true }
cubecl = { workspace = true, optional = true }

derive-new = { workspace = true }
half = { workspace = true, features = ["bytemuck"] }
num-traits = { workspace = true }
rand = { workspace = true }
rand_distr = { workspace = true }                    # use instead of statrs because it supports no_std
bytemuck = { workspace = true }

# The same implementation of HashMap in std but with no_std support (only needs alloc crate)
hashbrown = { workspace = true } # no_std compatible

# Serialization
serde = { workspace = true }
serde_bytes = { workspace = true }

[dev-dependencies]
rand = { workspace = true, features = ["std", "std_rng"] } # Default enables std

[package.metadata.docs.rs]
features = ["doc"]