-
line 269, in losses.py
one_hot = torch.zeros((labels[index].size(0), kwargs['out_features']), dtype=torch.bool)
here, is it id class number to 'out_features' ?
-
hi vincip,
I am learning about your code. And I find your code in LocomotionMPC_qpoases.m line192 is different from what i derived. Equ1 3 and 4 are same, but equ 2 is a little different.
What i d…
-
### LeetCode Username
sycode
### Problem Number, Title, and Link
1004. Max Consecutive Ones III https://leetcode.com/problems/max-consecutive-ones-iii/
### Bug Category
Missing test case *(Incorr…
-
Client is sending "0" as price when price was unspecified. Maybe send "-1" or some other default?
-
I am trying to make bitblas quantized weights to work with vLLM's tensor parallelism. In vLLM, tensor parallelism is achieved with column parallelism and row parallelism.
Similar to the reference v…
-
Is it possible to export models with complex weights? If so, how would I do that? For example,
```python
class cLinear(nn.Module):
def __init__(self, in_features, out_features, bias=True):
…
-
The datatrash doesn't contain only zeros as you have described in the repo description.
Pls, fix this, I need this software working.
Thanks
KROIA updated
4 years ago
-
I am trying to make the RHS of an ODEProblem Enzyme compatible. My function has the signature `(du, u, p, t)` and I try to differentiate `du` for `u` for constant `p` and `t`. I hit the error
```
ERRO…
-
### Is there an existing CVA6 bug for this?
- [x] I have searched the existing bug issues
### Bug Description
According to [CV32A65X Spec](https://docs.openhwgroup.org/projects/cva6-user-manual/04_…
-
Hi ! congrats on this wonderful job. After reading your paper, I'm really curious about one technique that you use.
In the paper, you said:
> To minimize the interference with the original model…