Merge 37f0b41ac6501266a661ebda3b1eff7bea9f3a1b into f6e34dd26772dd4a216be94a8899276c5dca9e43

inference/kernel.py

@@ -32,7 +32,7 @@ def act_quant_kernel(x_ptr, y_ptr, s_ptr, BLOCK_SIZE: tl.constexpr):
 
 def act_quant(x: torch.Tensor, block_size: int = 128) -> Tuple[torch.Tensor, torch.Tensor]:
     """
-    Quantizes the input tensor `x` using block-wise quantization.
+    Quantizes the input tensor `x` using block-wise quantization as implemented in the given function.
 
     Args:
         x (torch.Tensor): The input tensor to be quantized. Must be contiguous and its last dimension size must be divisible by `block_size`.