Add todos in metal/cuda

huggingface · Feb 24, 2025 · 6148daf · 6148daf
1 parent 48b3f9c
commit 6148daf
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 0 deletions.
diff --git a/candle-core/src/quantized/cuda.rs b/candle-core/src/quantized/cuda.rs
@@ -435,6 +435,9 @@ impl QCudaStorage {
             GgmlDType::Q5K => deq::<crate::quantized::BlockQ5K>(&buffer, block_len, &mut out)?,
             GgmlDType::Q6K => deq::<crate::quantized::BlockQ6K>(&buffer, block_len, &mut out)?,
             GgmlDType::Q8K => deq::<crate::quantized::BlockQ8K>(&buffer, block_len, &mut out)?,
+            GgmlDType::Iq4Xs | GgmlDType::Iq4Nl => {
+                todo!("CUDA does not support Iq4Xs or Iq4Nl yet.")
+            }
         }
 
         self.device

diff --git a/candle-core/src/quantized/metal.rs b/candle-core/src/quantized/metal.rs
@@ -225,6 +225,9 @@ impl From<GgmlDType> for candle_metal_kernels::GgmlDType {
             GgmlDType::Q8K => candle_metal_kernels::GgmlDType::Q8K,
             GgmlDType::F16 => candle_metal_kernels::GgmlDType::F16,
             GgmlDType::F32 => candle_metal_kernels::GgmlDType::F32,
+            GgmlDType::Iq4Xs | GgmlDType::Iq4Nl => {
+                todo!("Metal does not support Iq4Xs or Iq4Nl yet.")
+            }
         }
     }
 }