tracel-ai/burn · error

not implemented

Error message

not implemented

What it means

Stub guard in `BackendRouter`'s QTensorOps implementation: quantized tensor operations (`q_from_data`, `quantize`, etc.) are intentionally not implemented for the router backend; any call panics with `not implemented`.

Source

Thrown at crates/burn-router/src/ops/qtensor.rs:12

use burn_backend::{
    ExecutionError, FloatDType, Shape, TensorData,
    ops::QTensorOps,
    quantization::{QuantScheme, QuantizationParametersPrimitive},
    tensor::{Device, FloatTensor, QuantizedTensor},
};

use crate::{BackendRouter, RouterChannel};

impl<R: RouterChannel> QTensorOps<Self> for BackendRouter<R> {
    fn q_from_data(_data: TensorData, _device: &Device<Self>) -> QuantizedTensor<Self> {
        unimplemented!()
    }

    fn quantize(
        _tensor: FloatTensor<Self>,
        _scheme: &QuantScheme,
        _qparams: QuantizationParametersPrimitive<Self>,
    ) -> QuantizedTensor<Self> {
        unimplemented!()
    }

    fn quantize_dynamic(
        _tensor: FloatTensor<Self>,
        _scheme: &QuantScheme,
    ) -> QuantizedTensor<Self> {
        unimplemented!()
    }

    fn dequantize(_tensor: QuantizedTensor<Self>, _dtype: FloatDType) -> FloatTensor<Self> {

View on GitHub (pinned to d16f7ba2ed)

Solutions

1. Use a concrete backend that implements quantization (e.g., burn-ndarray, cubecl backends)
2. Dequantize the model weights before routing to this backend
3. Implement QTensorOps for the router channel if quantization routing is required

When it happens

Trigger: Thrown at crates/burn-router/src/ops/qtensor.rs:12 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of tracel-ai/burn@d16f7ba2ed (2026-09-05). Data as JSON: /api/errors/7b5306c150dee2b3. Report an issue: GitHub.