rob thijssen
5c957d08ec
Some checks failed
CI / Format (push) Successful in 36s
CI / Test (push) Failing after 53s
CI / Clippy (push) Successful in 2m35s
CI / Build cortex SRPM (push) Has been skipped
CI / Publish cortex to COPR (push) Has been skipped
CI / Build neuron SRPM (push) Has been skipped
CI / Publish neuron to COPR (push) Has been skipped
CI / Bump version in source (push) Has been skipped
Adds a manually-triggered workflow that builds CUDA-flavoured neuron binaries and a CPU cortex binary, packages them as Fedora RPMs, signs them, and rsyncs to the unstable channel at https://rpm.lair.cafe/fedora/43/x86_64/unstable/. Mirrors the build pipeline used by grenade/mistralrs-package. Pipeline: - prepare: derive {version,short_sha,commit_date} from the checkout; the prerelease Release stamp "0.1.YYYYMMDDgitSHORTSHA" sorts below the eventual "1" stable release. - build-cortex: cargo build --release -p cortex-cli on a rust runner. - build-neuron: matrix over ada (sm_89) and blackwell (sm_120) on cuda-13.0 runners; cargo build with features "cuda cudnn flash-attn" and CUDA_COMPUTE_CAP set per flavour. - package-{cortex,neuron}: rpmbuild on the rpm runner against the new prebuilt-binary specs in rpm/. - publish: import signing key, sign RPMs, rsync to oolon, createrepo_c --update, then regenerate packages.json for the UI. New specs are prebuilt-binary variants — they consume the artifact from the build job rather than running cargo at rpmbuild time. Each helexa-neuron-{flavour} package Conflicts with the other flavours and with helexa-neuron (the future source-build stable package) so one flavour is installed at a time on a given host. neuron crate gains cudnn and flash-attn feature flags forwarding to the corresponding candle features, so the CI build command compiles those kernels into the binary. sccache is intentionally NOT used in the prerelease jobs — CUDA compute cap isn't in its cache key, so flavours would mis-hit each other. Each prerelease build is a clean cargo build. Required Gitea secrets (already in place for cortex.spec / COPR workflow): - RPM_SIGNING_KEY, RPM_SIGNING_KEY_ID - RSYNC_SSH_KEY Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
67 lines
1.6 KiB
TOML
67 lines
1.6 KiB
TOML
[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. Without this feature, candle
|
|
# compiles for CPU only and Device::new_cuda calls fall back to CPU.
|
|
cuda = [
|
|
"candle-core/cuda",
|
|
"candle-nn/cuda",
|
|
"candle-transformers/cuda",
|
|
]
|
|
# 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
|
|
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"
|
|
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
|