llama.cpp
Add ReLU and SQR CUDA ops to fix Persimmon offloading
#4041

Merged

Add ReLU and SQR CUDA ops to fix Persimmon offloading #4041

KerfuffleV2 merged 2 commits into ggml-org:master from KerfuffleV2:fix-persimmon-cuda-offload

Add ReLU and SQR CUDA ops to fix Persimmon offloading

8df6fe60

KerfuffleV2 added bug

KerfuffleV2 added model

KerfuffleV2 added Nvidia GPU

KerfuffleV2 commented on 2023-11-12

SleepyYui commented on 2023-11-13

ggerganov approved these changes on 2023-11-13

Persimmon loader: More helpful error on CUDA/ROCM when offloading too…

3fad249b

KerfuffleV2 merged bb50a792 into master 2 years ago

Reviewers

ggerganov

SleepyYui

Assignees

No one assigned

Labels

bug model Nvidia GPU

Milestone

No milestone