-
Reply with your memo as a Comment. The memo should be responsive to this week's readings from David Wallace-Wells, with 300–500 words + 1 visual element (e.g., figure, image, hand-drawn picture, art, …
-
I'm opening the issue in an attempt to provide a platform for discussion on the project's future.
The project is unmaintained and it looks like the original contributors lost interest in it.
Curr…
-
Using RTX 3090 on vast.ai server with latest version.
It crashed 2 separate hosts, with the same setting that used to work before the update.
-
It's come to our attention that there is a zalgo bug in the `v1.4.44-liberty-2` release of colors.
Please know we are working right now to fix the situation and will have a resolution shortly.
!…
Marak updated
11 months ago
-
Hi, I'm using Amazon Linux 2
I try to use with GPU and I get the following error:
do you know how i can fix it?
(The error message is at the bottom)
`[root@amazonLinux vanitygen-plusplus]# n…
-
cuda: 35tokens/s
triton: 5tokens/s
I used ooba's webui only for cuda, because I've been unable to get triton to work with ooba's webui, I made sure i used the same parameters as in the command for…
-
Requirements 26 item C says: "The server SHALL respond synchronously if, according to the job control options in the process description, the process can be executed in either mode."
I think this i…
-
# [MYSTERY: LESS PEOPLE IN THE STREET](https://www.godlikeproductions.com/forum1/message5762217/pg2)
We are in a "Belief Reality System".
It is reactive.
It doesn't need anyone, but it reacts…
-
Hello!
I am testing the mistral-7b inference after quantization. I also want to test the impact of Flash Attention (sdpa, eager, fa2) on model inference. But the model decode latency is too high, and…
-
This turned out to be a major Twitter feature: being able to inline the text of a retweet while adding your own. It was done by manually copy-pasting the text before a feature was developed. How to go…