rob thijssen
1ebbe87651
Some checks failed
build-prerelease / Build cortex binary (push) Blocked by required conditions
CI / Test (push) Waiting to run
build-prerelease / Resolve version stamps (push) Successful in 29s
CI / Format (push) Successful in 40s
CI / Clippy (push) Successful in 2m23s
build-prerelease / Build neuron-blackwell (push) Has started running
build-prerelease / Build neuron-ampere (push) Has been cancelled
build-prerelease / Build neuron-ada (push) Has been cancelled
build-prerelease / Package cortex RPM (push) Has been cancelled
build-prerelease / Package helexa-neuron-ada RPM (push) Has been cancelled
build-prerelease / Package helexa-neuron-ampere RPM (push) Has been cancelled
build-prerelease / Package helexa-neuron-blackwell RPM (push) Has been cancelled
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Has been cancelled
CI / Build cortex SRPM (push) Has been cancelled
CI / Build neuron SRPM (push) Has been cancelled
CI / Publish cortex to COPR (push) Has been cancelled
CI / Publish neuron to COPR (push) Has been cancelled
CI / Bump version in source (push) Has been cancelled
Stage 8d (new): port the Gated DeltaNet CUDA kernels from
EricLBuehler/mistral.rs to close the ~500x decode performance gap
we measured on Qwen3.6-27B TP-2 (~12s/token in our pure-candle path
vs ~37 T/s in mistralrs on the same hardware).
This commit lays the build infrastructure with zero behavioural
change. Subsequent commits (8d-2 .. 8d-5) wire each kernel into the
qwen3_5 architecture and TP variant.
Added:
- `crates/neuron/build.rs` — uses `cudaforge::KernelBuilder` to compile
every `src/cuda/*.cu` file into `libneuroncuda.a` under the `cuda`
feature, then links it + `cudart`. Mirrors mistralrs's
`mistralrs-core/build.rs` setup verbatim (same NVCC flag set, same
sm_<80 bf16 gate).
- `crates/neuron/src/cuda/gdn.cu` — five kernels ported verbatim from
upstream:
* `gated_delta_rule_recurrence` (V-tiled per-token decode)
* `chunked_gated_delta_rule_recurrence` (BT=64 chunked prefill)
* `causal_conv1d_update` (single-token conv decode)
* `causal_conv1d_full` (multi-token conv prefill)
* `fused_gdn_gating` (beta = sigmoid(b); g = -exp(A_log) *
softplus(a + dt_bias))
- `crates/neuron/src/cuda/gdn.rs` — Rust wrappers around the kernels,
cudarc::CudaSlice::device_ptr boilerplate identical to upstream.
- `crates/neuron/src/cuda/ffi.rs` — `extern "C"` decls (subset of
upstream's ffi.rs covering only the five GDN kernels; MoE / SSM /
top-k decls land here when we absorb those too).
- `crates/neuron/src/cuda/mod.rs` — re-exports + module docs.
Cargo wiring: `cudaforge` added as an optional build-dep, activated
by the `cuda` feature. CPU build is unchanged (the `cuda/` module is
fully `#[cfg(feature = "cuda")]`). The cuda feature build inside the
patched container compiles `gdn.cu` (1 of 1 kernels) and links
clean.
Licensing: upstream files preserve their MIT origin via per-file
comment banners pointing to the mistralrs path. No behaviour-relevant
edits to the .cu kernels — local diff against upstream is just the
banner. The `.rs` wrappers and `ffi.rs` subset are also from upstream;
their structure (module path `crate::cuda::ffi::*`) matches identically
so future kernel imports drop in unchanged.
CPU clippy + 32 lib tests pass; `cargo clippy --features cuda` clean
inside the runner container.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
93 lines
2.8 KiB
TOML
93 lines
2.8 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 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
|