[package]
name = "neuron"
version.workspace = true
edition.workspace = true
license.workspace = true

[lib]
name = "neuron"
path = "src/lib.rs"

[[bin]]
name = "neuron"
path = "src/main.rs"

[features]
default = []
# Enables CUDA acceleration in candle and the cudarc/nccl bindings the
# TP worker pool uses. Without this feature, candle compiles for CPU
# only, Device::new_cuda calls fall back to CPU, and TP Init/sanity
# requests return Error{kind="cuda_feature_not_enabled"}.
cuda = [
    "candle-core/cuda",
    "candle-core/nccl",
    "candle-nn/cuda",
    "candle-transformers/cuda",
    "dep:cudarc",
    "dep:half",
    "dep:cudaforge",
]
# Use cuDNN for convolution / attention kernels. Requires CUDA.
cudnn = [
    "cuda",
    "candle-core/cudnn",
    "candle-nn/cudnn",
    "candle-transformers/cudnn",
]
# FlashAttention kernels. Requires CUDA.
flash-attn = [
    "cuda",
    "candle-transformers/flash-attn",
]
# Reserved for GPU-only integration tests in later stages.
cuda-integration = ["cuda"]

[dependencies]
cortex-core.workspace = true
tokio.workspace = true
axum.workspace = true
serde.workspace = true
serde_json.workspace = true
reqwest.workspace = true
tracing.workspace = true
tracing-subscriber.workspace = true
anyhow.workspace = true
async-trait.workspace = true
clap.workspace = true
thiserror.workspace = true
futures.workspace = true
tokio-stream.workspace = true
figment.workspace = true
toml.workspace = true

# candle for in-process inference. CUDA support is gated behind the
# crate's `cuda` feature (default off) so the workspace builds on
# non-CUDA hosts and CI runners.
candle-core = "0.10.2"
candle-nn = "0.10.2"
candle-transformers = "0.10.2"
# Direct dep on cudarc (matching candle's transitive version) so the
# TP worker pool can call cudarc::nccl::{Comm, Id} directly. Gated on
# the `cuda` feature; same toolchain requirement as candle's CUDA path.
cudarc = { version = "0.19", optional = true, default-features = false, features = ["nccl", "cuda-version-from-build-system"] }
# Used by the AllReduce CustomOp1 to type-dispatch on bf16/f16 candle
# storages. Matches candle-core's pinned major version to avoid double-
# compiling the `half` crate at conflicting versions.
half = { version = "2.5", optional = true }
tokenizers = { version = "0.22", default-features = false, features = ["onig"] }
hf-hub = { version = "0.4", features = ["tokio"] }

[dev-dependencies]
tokio = { workspace = true, features = ["test-util"] }
reqwest.workspace = true

[build-dependencies]
# Used by `build.rs` to compile `src/cuda/*.cu` into `libneuroncuda.a`
# under the `cuda` feature. Matches mistralrs's upstream build setup
# (their `mistralrs-core/build.rs` uses the same constructor).
cudaforge = { version = "0.1", optional = true }

[package.metadata.docs.rs]
# Skip the CUDA path on docs.rs (it lacks nvcc).
no-default-features = true