b616d024ad
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>
31 lines
969 B
TOML
31 lines
969 B
TOML
[package]
|
|
name = "ml-explainability"
|
|
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 = "Model explainability (integrated gradients) for Foxhunt ML"
|
|
|
|
[features]
|
|
default = ["cuda"]
|
|
cuda = ["candle-core/cuda", "candle-core/cudnn", "candle-nn/cuda", "candle-nn/cudnn"]
|
|
|
|
[dependencies]
|
|
ml-core = { path = "../ml-core", default-features = false }
|
|
candle-core = { git = "https://github.com/huggingface/candle", rev = "671de1db" }
|
|
candle-nn = { git = "https://github.com/huggingface/candle", rev = "671de1db" }
|
|
|
|
[dev-dependencies]
|
|
candle-core = { git = "https://github.com/huggingface/candle", rev = "671de1db" }
|
|
candle-nn = { git = "https://github.com/huggingface/candle", rev = "671de1db" }
|
|
|
|
[lints]
|
|
workspace = true
|