Issues 共 12
Quantizing q8p
#24 · ghost · 2024-08-21
How to see the parameters of a model
#23 · davidw0311 · 2024-03-19
Unable to include s4nnc inside bazel project
#22 · davidw0311 · 2024-02-06
Scaled dot product attention backward does not work with MacOS
#21 · brappier · 2023-12-20
Does ScaledDotProductAttention support backward pass?
#20 · brappier · 2023-12-17
Meta Flash Attention min OS version?
#19 · brappier · 2023-12-15
Loading the model with quantized weights , two times corrupts the model
#18 · brappier · 2023-12-09
How to combine models and save weights of the single combined model
#17 · brappier · 2023-11-24
SPM support
#16 · mseriukov · 2023-08-10
How to multipy a large tensor with smaller tensor
#14 · brappier · 2023-06-14