osobhandClaude Fable 5
1e3c604896
Meta-crates (Phase 2): - rtx-core / rtx-training / rtx-inference-stack gain cuda and metal features threading into their sub-crates; GPU was previously unreachable through the user-facing bundles. - rtx-training restores rtx-distributed (the hpc-channels blocker is gone) so the advertised DistributedTransformerTrainer resolves; drops the unused rtx-runtime dep. - rtx-transformers drops unused rtx-backend/rtx-backend-cpu deps (stale comment referenced a teacher that never used them). Never-compiled CUDA paths fixed (surfaced by the new feature wiring, verified on RTX 5060 Ti / CUDA 13.1): - rtx-compress build.rs: missing Path/Command/fs imports. - rtx-flash-attention flash_decode_forward: reborrow &mut kernel args. - rtx-transformers: rope kernel include path, cudarc 0.18 Arc<CudaModule>, PushKernelArg imports in jepa_gpu, edition-2024 ref patterns. - rtx-memory: full cudarc 0.18 port (CudaContext, stream-based alloc, DevicePtr accessors, error enum formatting) across gpu_pinning, gpu_transfer, gpu_real, gpu_allocator/arena, gpu_tests. JEPA (Phase 3): - JepaRunConfig::apply_cluster_plan consumes ClusterTrainingPlan (batch size, TP/DP, world size, total steps) so jepa_cluster is no longer standalone dead config; ViTSizeStr::approx_params_m feeds JepaParallelConfig::for_model_and_cluster. - WebDatasetShard::load reads real .tar shards from disk via the existing parser (gzip rejected explicitly); to_in_memory documented as synthetic/test-only. - New image-decode feature actually defines the dep for the previously unreachable cfg(feature = "image-decode") JPEG/PNG decode path. Co-Authored-By: Claude Fable 5 <[email protected]>
46 lines
1.4 KiB
TOML
46 lines
1.4 KiB
TOML
[package]
|
|
name = "rtx-inference-stack"
|
|
version = "1.0.0"
|
|
edition.workspace = true
|
|
rust-version = "1.92"
|
|
authors = ["RustyTorch Team"]
|
|
license = "MIT OR Apache-2.0"
|
|
repository = "https://github.com/rustytorch/rustytorch"
|
|
description = "RTX high-performance inference stack - Production model serving"
|
|
keywords = ["machine-learning", "inference", "serving", "production", "deployment"]
|
|
categories = ["science", "web-programming::http-server"]
|
|
|
|
[dependencies]
|
|
# Core
|
|
rtx-tensor = { path = "../../core/rtx-tensor", version = "1.0.0" }
|
|
rtx-runtime = { path = "../../core/rtx-runtime", version = "1.0.0" }
|
|
|
|
# Inference
|
|
rtx-inference = { path = "../../production/rtx-inference", version = "1.0.0" }
|
|
rtx-serving-api = { path = "../../production/rtx-serving-api", version = "1.0.0" }
|
|
rtx-streaming = { path = "../../production/rtx-streaming", version = "1.0.0" }
|
|
rtx-compress = { path = "../../training/rtx-compress", version = "1.0.0" }
|
|
|
|
[features]
|
|
default = []
|
|
# GPU inference via the engine's optional backends: candle + ONNX Runtime
|
|
# CUDA execution providers, plus CUDA tensor/runtime/compression support.
|
|
cuda = [
|
|
"rtx-tensor/cuda",
|
|
"rtx-runtime/cuda",
|
|
"rtx-compress/cuda",
|
|
"rtx-inference/candle-cuda",
|
|
"rtx-inference/onnx-cuda",
|
|
]
|
|
metal = [
|
|
"rtx-tensor/metal",
|
|
"rtx-runtime/metal",
|
|
"rtx-inference/candle-metal",
|
|
]
|
|
|
|
[dev-dependencies]
|
|
tokio-test = "0.4"
|
|
criterion = "0.5"
|
|
[lints]
|
|
workspace = true
|