07d0e60fe4
- Fork cudarc locally (vendor/cudarc): add CudaContext::load_cubin() that calls cuModuleLoadData directly — zero nvrtc dependency - Remove "nvrtc" feature from ml-core, ml-dqn, ml-ppo Cargo.toml - Replace all 89 Ptx::from_binary + load_module calls with load_cubin - ml-core cuda_autograd: wire 9 stub constructors to precompiled cubins (activation, elementwise, linear, loss, reduction, dropout, layer_norm, optimizer) - ml-core build.rs: compile 8 BF16-native CUDA kernels via nvcc - cubin_loader.rs: thin wrapper around CudaContext::load_cubin() - Fix size_of::<f32> in gpu_tensor.rs, stream_ops.rs, layer_norm.rs - Fix test data: Vec<f32> → Vec<half::bf16> for memcpy_htod - Stub ml-ppo/ml-dqn runtime compile_ptx calls (dead code) - backtest_metrics_kernel.cu: full native BF16 rewrite (no float) - backtest_env_kernel.cu: shared memory → __nv_bfloat16 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
46 lines
1.2 KiB
YAML
46 lines
1.2 KiB
YAML
on: [pull_request]
|
|
|
|
jobs:
|
|
cargo-check:
|
|
name: cargo-check
|
|
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
os: [ubuntu-latest, windows-latest]
|
|
version:
|
|
- cuda-11040
|
|
- cuda-11050
|
|
- cuda-11060
|
|
- cuda-11070
|
|
- cuda-11080
|
|
- cuda-12000
|
|
- cuda-12010
|
|
- cuda-12020
|
|
- cuda-12030
|
|
- cuda-12040
|
|
- cuda-12050
|
|
- cuda-12060
|
|
- cuda-12080
|
|
- cuda-12090
|
|
- cuda-13000
|
|
- cuda-13010
|
|
|
|
runs-on: ${{ matrix.os }}
|
|
|
|
steps:
|
|
- uses: actions/checkout@v2
|
|
- uses: actions-rs/toolchain@v1
|
|
with:
|
|
profile: minimal
|
|
toolchain: stable
|
|
override: true
|
|
- uses: actions-rs/cargo@v1
|
|
with:
|
|
command: check
|
|
args: --all-targets -F ${{ matrix.version }},cudnn,nccl,cusolver,cusolvermg,cusparse,cufile,cupti,nvtx,cufft,cutensor
|
|
- uses: actions-rs/cargo@v1
|
|
with:
|
|
command: check
|
|
args: --all-targets --no-default-features -F ${{ matrix.version }},no-std,cudnn,cublas,cublaslt,nvrtc,driver,curand,nccl,cusolver,cusolvermg,cusparse,cufile,cupti,nvtx,cufft,cutensor,dynamic-loading
|