llmcompressor.observers.min_max
Classes:
-
MemorylessMinMaxObserver–Compute quantization parameters by taking the min/max of the observed value.
-
MinMaxObserver–Compute quantization parameters by taking the moving average of min/max values.
-
StaticMinMaxObserver–Compute quantization parameters by taking the min/max of all observed values.
MemorylessMinMaxObserver
Bases: Observer
Compute quantization parameters by taking the min/max of the observed value.
Source code in src/llmcompressor/observers/base.py
MinMaxObserver
Bases: Observer
Compute quantization parameters by taking the moving average of min/max values.
Source code in src/llmcompressor/observers/min_max.py
StaticMinMaxObserver
Bases: MemorylessMinMaxObserver
Compute quantization parameters by taking the min/max of all observed values.