[Add comment and reference of param observer]

Author: Joey Tsai

backends/qualcomm/quantizer/observers/per_channel_param_observer.py

@@ -4,6 +4,10 @@
 
 # TODO move to torch/ao/quantization/observer.py.
 class PerChannelParamObserver(UniformQuantizationObserverBase):
+    """
+    Minimize quantization loss caused by outlier via linear search. More details can be found at https://arxiv.org/pdf/2209.13325
+    """
+
     def __init__(
         self,
         ch_axis=0,