Three fixes for GPU PER hot path: 1. IQN quantile loss used empty CPU weights Vec instead of GPU-resident weights_tensor_cached — caused CUDA_ERROR_ILLEGAL_ADDRESS from uninitialized GPU memory. Now uses cached GPU tensor matching C51 and standard DQN paths. 2. GpuPrioritized add()/add_batch() replaced with StagedGpuBuffer: add() stages on CPU (Vec::push, zero GPU ops), sample() batch-flushes staging→GPU in one DMA before sampling. Production path (insert_batch_tensors) bypasses staging entirely — GPU→GPU with zero CPU. 3. All 9 ML sub-crates default to cuda feature so `cargo test -p ml-dqn` exercises GPU code paths on CUDA workstations. CI service crates use default-features=false, unaffected. Test results: 350 passed (was 343+7 failed), 0 failed, 1 ignored. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
68 lines
2.0 KiB
TOML
68 lines
2.0 KiB
TOML
[package]
|
|
name = "ml-core"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
rust-version.workspace = true
|
|
authors.workspace = true
|
|
license.workspace = true
|
|
repository.workspace = true
|
|
homepage.workspace = true
|
|
documentation.workspace = true
|
|
publish.workspace = true
|
|
keywords.workspace = true
|
|
categories.workspace = true
|
|
description = "Shared ML types, traits, and infrastructure for Foxhunt"
|
|
|
|
[features]
|
|
default = ["cuda"]
|
|
cuda = ["candle-core/cuda", "candle-core/cudnn", "candle-nn/cuda", "candle-nn/cudnn"]
|
|
s3-storage = ["aws-config", "aws-sdk-s3", "aws-types", "aws-credential-types", "urlencoding"]
|
|
high-precision = ["rust_decimal/serde-float"]
|
|
mimalloc-allocator = ["mimalloc"]
|
|
simd = []
|
|
gc = []
|
|
financial = []
|
|
minimal-inference = []
|
|
nccl = ["cuda"]
|
|
|
|
[dependencies]
|
|
# Core (needed by types in lib.rs)
|
|
serde = { workspace = true, features = ["derive"] }
|
|
serde_json.workspace = true
|
|
thiserror.workspace = true
|
|
anyhow.workspace = true
|
|
chrono.workspace = true
|
|
tracing.workspace = true
|
|
rust_decimal.workspace = true
|
|
async-trait.workspace = true
|
|
futures.workspace = true
|
|
tokio.workspace = true
|
|
once_cell = "1.19"
|
|
dashmap = { workspace = true }
|
|
rayon.workspace = true
|
|
num_cpus = "1.16"
|
|
candle-core = { git = "https://github.com/huggingface/candle", rev = "671de1db" }
|
|
candle-nn = { git = "https://github.com/huggingface/candle", rev = "671de1db" }
|
|
candle-optimisers = { git = "https://github.com/KGrewal1/optimisers" }
|
|
common.workspace = true
|
|
config.workspace = true
|
|
uuid.workspace = true
|
|
parking_lot = { version = "0.12", features = ["hardware-lock-elision"] }
|
|
ndarray = { workspace = true, features = ["rayon"] }
|
|
|
|
# Optional
|
|
mimalloc = { version = "0.1", optional = true }
|
|
aws-config = { version = "1.1", optional = true }
|
|
aws-sdk-s3 = { version = "1.14", optional = true }
|
|
aws-types = { version = "1.1", optional = true }
|
|
aws-credential-types = { version = "1.1", optional = true }
|
|
urlencoding = { version = "2.1", optional = true }
|
|
|
|
[dev-dependencies]
|
|
tokio = { workspace = true, features = ["test-util", "macros"] }
|
|
tempfile = "3.12"
|
|
approx = "0.5"
|
|
|
|
[lints]
|
|
workspace = true
|