-
Notifications
You must be signed in to change notification settings - Fork 2.9k
Pull requests: PaddlePaddle/PaddleNLP
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
support Llama3.1 8B 128K generation on single GPU 80GB
#8811
opened Jul 25, 2024 by
GuoxiaWang
Loading…
Do Not Merge, [XPU], use paddle's fused_rms_norm instead of paddle_xpu_nn's in llama
#8746
opened Jul 10, 2024 by
cqulilujia
Loading…
Hybrid quantization algorithm based on lqlora
contributor
#8724
opened Jul 7, 2024 by
Liebele
Loading…
Previous Next
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.