feat: purpose-built inference optimizations with 30x per-token speedup #43
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: CI | |
| on: | |
| push: | |
| branches: ["main", "master"] | |
| pull_request: | |
| branches: ["main", "master"] | |
| jobs: | |
| test-rust: | |
| name: Test (Rust) | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Install Rust toolchain | |
| uses: dtolnay/rust-toolchain@stable | |
| - name: Cache cargo | |
| uses: Swatinem/rust-cache@v2 | |
| - name: Format check | |
| run: cargo fmt --all --check | |
| - name: Clippy | |
| run: cargo clippy --workspace --all-targets -- -D warnings | |
| - name: Test workspace | |
| run: cargo test --workspace --all-targets | |
| - name: AI overhead gate | |
| run: | | |
| WRITE_OPS=5000 \ | |
| READ_OPS=2500 \ | |
| KEYSPACE=1500 \ | |
| MAX_WRITE_DROP_PCT=90 \ | |
| MAX_P95_INCREASE_PCT=150 \ | |
| MAX_P99_INCREASE_PCT=150 \ | |
| ./scripts/ai_overhead_gate.sh | |
| test-native: | |
| name: Test (Native Feature) | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Install Rust toolchain | |
| uses: dtolnay/rust-toolchain@stable | |
| - name: Cache cargo | |
| uses: Swatinem/rust-cache@v2 | |
| - name: Install C++ toolchain | |
| run: sudo apt-get update && sudo apt-get install -y build-essential | |
| - name: Verify C++ toolchain | |
| run: c++ --version | |
| - name: Clippy (native) | |
| run: cargo clippy --workspace --all-targets --features native -- -D warnings | |
| - name: Test workspace with native feature | |
| run: cargo test --workspace --all-targets --features native |