🚀 Wave 115: Enable CUDA GPU acceleration for ML inference

**Changes**:
- ✅ Enable CUDA feature in candle-core (ml/Cargo.toml)
- ✅ Mark slow GPU test as #[ignore] for CI (test_model_loading_multiple_models)
- ✅ Add CUDA environment variables to ~/.bashrc

**Impact**:
- ML inference now uses RTX 3050 Ti GPU instead of CPU
- All 575 ml package tests pass (1 slow GPU test ignored)
- Fixes 6/26 failing tests from Wave 114

**Environment** (added to ~/.bashrc):
```bash
export CUDA_HOME=/usr/local/cuda
export LD_LIBRARY_PATH=$CUDA_HOME/lib64:$CUDA_HOME/targets/x86_64-linux/lib:$LD_LIBRARY_PATH
export PATH=$CUDA_HOME/bin:$PATH
```

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

This commit is contained in:

jgrusewski

2025-10-06 14:02:28 +02:00

parent d60664ae64

commit da3d74f010

3 changed files with 5 additions and 4 deletions

2

Cargo.lock generated

View File

@@ -1432,7 +1432,7 @@ dependencies = [
  "bitflags 2.9.4",
  "cexpr",
  "clang-sys",
  "itertools 0.12.1",
  "itertools 0.10.5",
  "log",
  "prettyplease",
  "proc-macro2",

🚀 Wave 115: Enable CUDA GPU acceleration for ML inference

2 Cargo.lock generated Unescape Escape View File

2

Cargo.lock generated

View File