* change fallback data type from F16 to F32
* only fallback to F32 for 1D or very small tensors
* change exception fallback type
* blacklist before small tensor check
Benefit of FP32 for dequantization seems less noticable and feels more like a sidegrade due to differences in numerical precision. Was causing issues with memory not being freed.
#16
Use FP32 to do the calculations while dequantizing to improve existing Q8_0 quants and to avoid double dtype conversion.
Add Q4_1 and Q5_1 dequant kernels
City