{"record":{"id":"bcfc3dc43ab8863c","repo":"huggingface/candle","slug":"compile-with-features-flash-attn-bcfc3d","errorCode":null,"errorMessage":"compile with '--features flash-attn'","messagePattern":"compile with '--features flash-attn'","errorType":"panic","errorClass":null,"httpStatus":null,"severity":"error","filePath":"candle-transformers/src/models/granite.rs","lineNumber":212,"sourceCode":"    span: tracing::Span,\n    span_rot: tracing::Span,\n    max_position_embeddings: usize,\n}\n\n#[cfg(feature = \"flash-attn\")]\nfn flash_attn(\n    q: &Tensor,\n    k: &Tensor,\n    v: &Tensor,\n    softmax_scale: f32,\n    causal: bool,\n) -> Result<Tensor> {\n    candle_flash_attn::flash_attn(q, k, v, softmax_scale, causal)\n}\n\n#[cfg(not(feature = \"flash-attn\"))]\nfn flash_attn(_: &Tensor, _: &Tensor, _: &Tensor, _: f32, _: bool) -> Result<Tensor> {\n    unimplemented!(\"compile with '--features flash-attn'\")\n}\n\nimpl CausalSelfAttention {\n    fn apply_rotary_emb(&self, x: &Tensor, index_pos: usize, cache: &Cache) -> Result<Tensor> {\n        let _enter = self.span_rot.enter();\n        let (_b_sz, _, seq_len, _hidden_size) = x.dims4()?;\n        let cos = cache.cos.narrow(0, index_pos, seq_len)?;\n        let sin = cache.sin.narrow(0, index_pos, seq_len)?;\n        candle_nn::rotary_emb::rope(x, &cos, &sin)\n    }\n\n    fn forward(\n        &self,\n        x: &Tensor,\n        index_pos: usize,\n        block_idx: usize,\n        cache: &mut Cache,\n    ) -> Result<Tensor> {","sourceCodeStart":194,"sourceCodeEnd":230,"githubUrl":"https://github.com/huggingface/candle/blob/d5fee525bfde3273eb7c9b75fd2bc4937be867ca/candle-transformers/src/models/granite.rs#L194-L230","documentation":"granite.rs defines a `flash_attn` function whose fallback build (without the `flash-attn` cargo feature) panics with `unimplemented!`. When `CausalSelfAttention` forward selects the flash path because `config.use_flash_attn` is true, this stub is hit and the program aborts.","triggerScenarios":"Running the Granite model with `use_flash_attn: true` in Config while compiled without `--features flash-attn`.","commonSituations":"Checkpoint config enables flash attention; default builds without the feature; attempting to use the feature on non-CUDA systems where candle-flash-attn cannot run.","solutions":["Recompile with the feature: `cargo run --release --features candle-transformers/flash-attn` (CUDA required).","Set `config.use_flash_attn = false` before creating the model.","If you cannot enable CUDA, keep the default attention implementation and accept slower inference."],"exampleFix":"// before\ncargo build --release\n// after\ncargo build --release --features candle-transformers/flash-attn","handlingStrategy":"validation","validationCode":"#[cfg(not(feature = \"flash-attn\"))]\nif config.use_flash_attn {\n    return Err(anyhow::anyhow!(\"granite: rebuild with --features candle-transformers/flash-attn or set use_flash_attn=false\"));\n}","typeGuard":"fn flash_ok(cfg: &granite::Config) -> bool {\n    !cfg.use_flash_attn || cfg!(feature = \"flash-attn\")\n}","tryCatchPattern":"let config = if flash_ok(config) { config } else { config.with_flash_attn(false) };","preventionTips":["Validate config flags against enabled cargo features at startup","Keep CUDA-specific features behind explicit feature checks","Search checkpoint config.json for flash-attention keys when porting models","Run a one-token forward pass as a startup self-check"],"tags":["rust","candle","feature-flag","flash-attention","panic"],"backgroundTag":"missing-cargo-feature","analyzedSha":"d5fee525bfde3273eb7c9b75fd2bc4937be867ca","analyzedAt":"2026-09-02T00:15:47.023Z","contentChangedAt":null,"schemaVersion":2},"datasetVersion":"2026-09-09T06:17:21.866Z"}