Merge pull request #1 from DrJesseGlass/examples/add/smolLM3-chat

Add chat template

Author: DrJesseGlass

.github/workflows/ci_cuda.yaml

@@ -10,10 +10,9 @@ jobs:
       group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
       cancel-in-progress: true
     runs-on:
-      group: aws-g4dn-2xlarge
+      group: aws-g5-4xlarge-cache
     container:
-      image: nvidia/cuda:12.3.1-devel-ubuntu22.04
-      options: --gpus 0 
+      image: nvidia/cuda:13.0.2-cudnn-devel-ubuntu24.04
     if: ${{ github.event.pull_request.head.repo.full_name == github.event.pull_request.base.repo.full_name }}
     permissions:
       contents: write
@@ -22,13 +21,15 @@ jobs:
       # with sigstore/fulcio when running outside of PRs.
       id-token: write
       security-events: write
+    env:
+      CUDA_COMPUTE_CAP: 86
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v5
       - name: Install dependencies
-        run: apt-get update && apt install curl build-essential libssl-dev protobuf-compiler pkg-config -y
+        run: apt update && apt install curl build-essential libssl-dev protobuf-compiler pkg-config -y
       - name: Install Rust Stable
-        uses: actions-rust-lang/setup-rust-toolchain@v1
+        uses: dtolnay/rust-toolchain@stable
       - uses: Swatinem/rust-cache@v2
       - name: Test (cuda)
         run: cargo test --features cuda

.github/workflows/maturin.yml

@@ -20,17 +20,15 @@ jobs:
         os: [ubuntu-latest] # For now, only test on Linux
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Install Rust
-        uses: actions-rs/toolchain@v1
-        with:
-          toolchain: stable
+        uses: dtolnay/rust-toolchain@stable
 
       - name: Install Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
-          python-version: 3.11
+          python-version: 3.13
           architecture: "x64"
 
       - name: Cache Cargo Registry
@@ -42,8 +40,8 @@ jobs:
       - name: Install Protoc
         uses: arduino/setup-protoc@v2
         with:
-            version: "25.0"
-            repo-token: ${{ secrets.GITHUB_TOKEN }}
+          version: "25.0"
+          repo-token: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Install
         working-directory: ./candle-pyo3

.github/workflows/python.yml

@@ -13,81 +13,68 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, windows-latest, macOS-latest]
-        rust: [stable]
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/checkout@v5
+      - uses: actions/setup-python@v6
         with:
-          python-version: "3.11"
+          python-version: "3.13"
       - name: Remove cargo config (macOS ring crate fix)
         if: runner.os == 'macOS'
         run: rm -f .cargo/config.toml
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          toolchain: ${{ matrix.rust }}
-          override: true
-      - uses: actions-rs/cargo@v1
-        with:
-          command: check
-          args: --workspace
+      - uses: dtolnay/rust-toolchain@stable
+      - run: cargo check --workspace
 
   test:
     name: Test Suite
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
         os: [ubuntu-latest, windows-latest, macOS-latest]
-        rust: [stable]
     steps:
-      - name: Delete huge unnecessary tools folder
+      - name: Free disk space (Linux)
         if: runner.os == 'Linux'
-        run: rm -rf /opt/hostedtoolcache
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+        run: |
+          sudo rm -rf /opt/hostedtoolcache
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /opt/ghc
+          df -h
+      - uses: actions/checkout@v5
+      - uses: actions/setup-python@v6
         with:
-          python-version: "3.11"
+          python-version: "3.13"
       - name: Remove cargo config (macOS ring crate fix)
         if: runner.os == 'macOS'
         run: rm -f .cargo/config.toml
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          toolchain: ${{ matrix.rust }}
-          override: true
-      - uses: actions-rs/cargo@v1
-        with:
-          command: test
-          args: --workspace
+      - uses: dtolnay/rust-toolchain@stable
+      - name: Install lld (Linux only)
+        if: runner.os == 'Linux'
+        run: sudo apt-get update && sudo apt-get install -y lld
+      - name: Run tests (with lld on Linux)
+        if: runner.os == 'Linux'
+        env:
+          RUSTFLAGS: "-C link-arg=-fuse-ld=lld"
+        run: cargo test --workspace
+      - name: Run tests (Windows & macOS)
+        if: runner.os != 'Linux'
+        run: cargo test --workspace
 
   fmt:
     name: Rustfmt
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions-rs/toolchain@v1
+      - uses: actions/checkout@v5
+      - uses: dtolnay/rust-toolchain@stable
         with:
-          profile: minimal
-          toolchain: stable
-          override: true
-      - run: rustup component add rustfmt
-      - uses: actions-rs/cargo@v1
-        with:
-          command: fmt
-          args: --all -- --check
+          components: rustfmt
+      - run: cargo fmt --all -- --check
 
   clippy:
     name: Clippy
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - uses: actions-rs/toolchain@v1
-        with:
-          profile: minimal
-          toolchain: stable
-          override: true
-      - run: rustup component add clippy
-      - uses: actions-rs/cargo@v1
+      - uses: dtolnay/rust-toolchain@stable
         with:
-          command: clippy
-          args: --workspace --tests --examples --benches -- -D warnings
+          components: clippy
+      - run: cargo clippy --workspace --tests --examples --benches -- -D warnings

.github/workflows/rust-ci.yml

@@ -7,9 +7,9 @@ jobs:
   trufflehog:
     runs-on: ubuntu-latest
     steps:
-    - name: Checkout code
-      uses: actions/checkout@v4
-      with:
-        fetch-depth: 0
-    - name: Secret Scanning
-      uses: trufflesecurity/trufflehog@main
+      - name: Checkout code
+        uses: actions/checkout@v5
+        with:
+          fetch-depth: 0
+      - name: Secret Scanning
+        uses: trufflesecurity/trufflehog@main

.github/workflows/trufflehog.yml

@@ -12,6 +12,7 @@ Cargo.lock
 # editor config
 .helix
 .vscode
+.zed
 
 # These are backup files generated by rustfmt
 **/*.rs.bk

.gitignore

@@ -45,7 +45,7 @@ candle-onnx = { path = "./candle-onnx", version = "0.9.2-alpha.1" }
 candle-transformers = { path = "./candle-transformers", version = "0.9.2-alpha.1" }
 clap = { version = "4.2.4", features = ["derive"] }
 criterion = { version = "0.7.0", default-features = false }
-cudarc = { version = "0.17.3", features = [
+cudarc = { version = "0.18.1", features = [
     "std",
     "cublas",
     "cublaslt",
@@ -65,7 +65,7 @@ half = { version = "2.5.0", features = [
     "use-intrinsics",
     "rand_distr",
 ] }
-float8 = { version = "0.4.2", features = [
+float8 = { version = "0.5.0", features = [
     "num-traits",
     "rand_distr",
 ] }
@@ -77,6 +77,7 @@ image = { version = "0.25.2", default-features = false, features = [
 imageproc = { version = "0.24.0", default-features = false }
 intel-mkl-src = { version = "0.8.1", features = ["mkl-static-lp64-iomp"] }
 libc = { version = "0.2.147" }
+libm = { version = "0.2.15" }
 log = "0.4"
 memmap2 = { version = "0.9.3", features = ["stable_deref_trait"] }
 num_cpus = "1.15.0"
@@ -85,7 +86,7 @@ parquet = { version = "51.0.0" }
 rand = "0.9.0"
 rand_distr = "0.5.1"
 rayon = "1.7.0"
-safetensors = "0.4.1"
+safetensors = "0.6.0"
 serde = { version = "1.0.171", features = ["derive"] }
 serde_plain = "1.0.2"
 serde_json = "1.0.99"

.vscode/settings.json

@@ -22,6 +22,7 @@ half = { workspace = true }
 float8 = { workspace = true }
 intel-mkl-src = { workspace = true, optional = true }
 libc = { workspace = true, optional = true }
+libm = { workspace = true }
 memmap2 = { workspace = true }
 num-traits = { workspace = true }
 num_cpus = { workspace = true }

Cargo.toml

@@ -38,8 +38,7 @@ fn criterion_benchmark(c: &mut Criterion) {
         run_affine_benchmark(c, &device, DType::F32, "affine_f32");
         run_affine_benchmark(c, &device, DType::F16, "affine_f16");
         run_affine_benchmark(c, &device, DType::BF16, "affine_bf16");
-        #[cfg(feature = "metal")]
-        continue;
+        #[cfg(not(feature = "metal"))]
         run_affine_benchmark(c, &device, DType::F8E4M3, "affine_fp8");
     }
 }