rob thijssen
8d7b099b36
Some checks failed
build-prerelease / Package cortex RPM (push) Blocked by required conditions
CI / Format (push) Successful in 35s
build-prerelease / Resolve version stamps (push) Successful in 39s
CI / Clippy (push) Successful in 2m18s
CI / Test (push) Successful in 4m28s
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
build-prerelease / Build neuron-blackwell (push) Successful in 3m51s
build-prerelease / Build cortex binary (push) Successful in 4m13s
build-prerelease / Build neuron-ada (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
build-prerelease / Build neuron-ampere (push) Has been cancelled
Replaces load_fused_qkv_slice_2d/_3d with reads from a separate MmapedSafetensors handle. Each per-rank fused tensor is built by reading the three region byte-slices directly from the mmap, concatenating them host-side, and uploading as one device allocation — no full-fused-tensor device materialisation. The prior approach allocated a ~100 MB transient device tensor per linear-attention layer; on Qwen3.6-27B with 48 linear-attn layers that's ~4.8 GB of allocator churn during load — enough to fragment the cuda caching allocator on a tight-VRAM 32 GB consumer GPU, which is what triggered the layer-22 up_proj OOM seen on beast. Threading: MmapedSafetensors flows worker → ForCausalLM → Model → DecoderLayer → GatedDeltaNet::load. Both leader (mod.rs) and worker (worker.rs) construct their own mmap; Linux's page cache shares the underlying pages. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
98 lines
3.1 KiB
TOML
98 lines
3.1 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"] }
|
|
# Direct dep on `safetensors` (re-exported by candle but its `TensorView`
|
|
# / `slice::IndexOp` types are public-but-not-re-exported). Used by the
|
|
# tp `fused_load` module to read per-rank slices of fused QKV tensors
|
|
# without materialising the full tensor on device.
|
|
safetensors = "0.7"
|
|
|
|
[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
|