-
FP8 is very useful in training or inference in LLM. Does flash attention support FP8?
Thank you~
-
There's an error message at the KSamplerTheMisto node, and the workflow can't complete. My GPU is a 2080ti.
"NotImplementedError: No operator found for `memory_efficient_attention_forward` with inp…
-
Yesterday I encountered this message:
I did what I normally do, i.e. search the Zotero Short Title in Zotero standalone, merge the two items, and then synchronise, but it did not make the error…
-
Great interface, I really like it.
But every few seconds I get a 10/15 frame drop causing tearing on the screen.
Since I started using it WOW randomly freeze in Instances.
Disabling DarkUI …
-
The crashes are frequent and intermittent, sometimes only steam is open, no game at all, and it crashes.
terminal output
```
[gamescope] [Info] console: gamescope version undefined
ATTENTION:…
-
Opening this issue so we don't forget: Once #1545 is merged, let's also add sliding window attention to Mistral 0.1
rasbt updated
2 months ago
-
See this excerpt from https://dev.azure.com/Lightning-AI/lightning/_build/results?buildId=215225&view=logs&j=5b0799f7-725e-5b16-9b83-c0a5a25d03f0&t=97651ec4-0b0f-5455-bbb5-3c30427a0a7e
```
FAILED …
-
I got the following error message when doing "make -j10"
```
CMake Error at ctranslate2_generated_flash_fwd_split_hdim96_fp16_sm80.cu.o.Release.cmake:280 (message):
Error generating file
/work…
-
Thank you very much for your excellent work. I wonder rpb should be added to attention weight in shape of [K, K]. However, the shape of rpb in 2d NATTEN is [2K-1,2K-1]. It is hard for me to find the …
-
lucidrains & zhuzilin were hard working the last days and have completed the following two ring-attention implementations:
- [lucidrains/ring-attention-pytorch](https://github.com/lucidrains/ring-a…