0seba

When calculating the balance of the underlying coins [here](https://github.com/curvefi/curve-subgraph/blob/fa26cd2f8a8d42f76c5e0e897469740508d70f43/src/services/pools/coins.ts#L49) the decimals are not used (which causes it default to 18 afaik), one example in which this causes problems is in...

Is there support to run ANE accelerated loops/while_loop?

1

Hi, I've been experimenting with while_loop (s), but I haven't had any success making them run accelerated on the ANE, and neither the GPU. Is it even possible for them...

How to replicate

1

Hey, I got an interest in your work and I'm trying to replicate the results. What I understood is that I had to run the `performance_match.py` file in the mnist...

[BUG] RMSNorm Implementation

1

I think you should be dividing by the scale in the following line https://github.com/kyegomez/zeta/blob/7dbb6a62f83413977a922d5fc6dec1b11f734bc3/zeta/nn/modules/rms_norm.py#L35 This this the scale definition https://github.com/kyegomez/zeta/blob/7dbb6a62f83413977a922d5fc6dec1b11f734bc3/zeta/nn/modules/rms_norm.py#L29C9-L29C31 ```python self.scale = dim**-0.5 ``` And RMSNorm formula  Edit:...

not create new symbol with immutable shape convolution. #1867

7

## 🌱 Hi, according to this [PR](https://github.com/apple/coremltools/pull/1867/files) which looked to be merged, when a convolution does not mutate dimension size for a symbolic shape, no new symbol should be created,...

Error on mixing shapes of multiple enumerated shape inputs

4

## 🐞Describing the bug I have a program with 3 inputs, all have a flexible enumerated shape, two share the same shape. The input shapes are: - `shapes_1 = [(1,...

Weights are shared across the MLP layers

1

See this https://github.com/linkedin/Liger-Kernel/pull/269 . Confirmed that weights are shared for vicuna 7b ~~Also, for some reason I couldn't find, not all layers have an `res_connection` linear layer~~ Finally, from the...

Multifunction consumes linearly increasing memory in the number of functions, even with all the weights shared

1

## 🌱 Describe your Feature Request Hi, when creating a multifunction with many functions that reuses the same weights for all cases, the memory increases on the number of functions....

random_categorical returns float when it should return int

2

I tried casting the output to int, but that fails