-
-
Hello，thank you for your outstanding work!
We couldn’t locate any theoretical insights or perspectives related to LUT quantization in the referenced paper, and while reading through the source code, …
-
## Context
What's your version of `nuqs`?
```
2.1.1
```
What framework are you using?
```
Operating System:
Platform: darwin
Arch: arm64
Version: Darwin Kernel Version 23.6…
-
Currently, we only take advantage of savings for computing the kernel gram matrix, and computing a gram solve in GP predictions.
We neglect:
- Efficiency of matrix solves and log-determinants…
-
For distributing large computations but also application such as position dependent PSF kernels it would really useful to have a split and merge scheme for `Map` objects. There are many thing to be c…
-
### System Info
HW
- EC2: g6e.12x
- GPU: L40S
- CUDA: 550.127.05
- Branch: commit 201135e58aa525af7e523d091d4c9584229524bc (HEAD, tag: v0.13.0)
Data
- Model: Llama-2-7b-hf
### Who can help?
@bys…
-
Posted here following discussion with @rhugonnet
Currently, `xdem` [calculates terrain coefficients](https://github.com/GlacioHack/xdem/blob/main/xdem/terrain.py) over a 3x3 window following Zeven…
-
# Summary
Current ACL integration [prohibits](https://github.com/oneapi-src/oneDNN/blob/f17db7cce721d60d37479c61f18d7876f79a9ed2/src/cpu/aarch64/acl_post_ops.hpp#L147-L148) first post op fusion into …
-
Hi, appreciate this wonderful repo!
I want to know if it is possible to rewrite the attention-related operations to support half precision model? I am new to CUDA code and have no idea on what sho…
-
# Description
## Bug
If the score computation associated to a trial of hyperparameter tuning takes too long, the patience of `BayesOptSearch` saturates because of duplicated configurations.
Thi…