huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-16 02:38:10 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
c3176f0dfb8ace213e4a499918da21bc5712a107
candle/candle-examples/examples
History
Laurent Mazare c3176f0dfb Flash-attention support in stable diffusion (#487) 
* Add flash-attention for the stable-diffusion example.

* Change the dtype.

* Silly fix.

* Another fix.

* Revert the dtype back to the query dtype after apply flash-attn.
2023-08-17 12:16:40 +01:00
..
bert
Add a cuda kernel for upsampling. (#441)
2023-08-14 13:12:17 +01:00
bigcode
Add a cuda kernel for upsampling. (#441)
2023-08-14 13:12:17 +01:00
custom-ops
Relax the requirements on CustomOp. (#486)
2023-08-17 11:12:05 +01:00
falcon
Add a cuda kernel for upsampling. (#441)
2023-08-14 13:12:17 +01:00
llama
Layer norm tweaks (#482)
2023-08-17 10:07:13 +01:00
llama2-c
Layer norm tweaks (#482)
2023-08-17 10:07:13 +01:00
llama_multiprocess
Relax the requirements on CustomOp. (#486)
2023-08-17 11:12:05 +01:00
mnist-training
Add the candle-datasets crate (#322)
2023-08-05 08:56:50 +01:00
musicgen
Remove the embedding ops in favor of index-select. (#299)
2023-08-02 05:42:11 +01:00
quantized
Layer norm tweaks (#482)
2023-08-17 10:07:13 +01:00
stable-diffusion
Flash-attention support in stable diffusion (#487)
2023-08-17 12:16:40 +01:00
whisper
Add a cuda kernel for upsampling. (#441)
2023-08-14 13:12:17 +01:00