llama.cpp
musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy
#13647
Merged

musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy #13647

yeahdongcn merged 5 commits into ggml-org:master from makllama:xd/dnn
yeahdongcn
yeahdongcn musa: fix build warning (unused parameter)
46b3f7de
yeahdongcn yeahdongcn requested a review from JohannesGaessler JohannesGaessler 1 year ago
yeahdongcn yeahdongcn requested a review from ngxson ngxson 1 year ago
yeahdongcn yeahdongcn requested a review from ggerganov ggerganov 1 year ago
github-actions github-actions added documentation
github-actions github-actions added Nvidia GPU
github-actions github-actions added devops
github-actions github-actions added ggml
yeahdongcn musa: upgrade MUSA SDK version to rc4.0.1
11edfe93
yeahdongcn musa: use mudnn::Unary::IDENTITY op to accelerate D2D memory copy
14828714
yeahdongcn yeahdongcn force pushed to 14828714 1 year ago
JohannesGaessler
JohannesGaessler commented on 2025-05-20
yeahdongcn Update ggml/src/ggml-cuda/cpy.cu
c66ccb33
yeahdongcn
yeahdongcn
JohannesGaessler
JohannesGaessler approved these changes on 2025-05-20
JohannesGaessler
ggerganov
yeahdongcn
yeahdongcn musa: remove MUDNN_CHECK_GEN and use CUDA_CHECK_GEN instead in MUDNN_…
de631ed4
yeahdongcn
yeahdongcn yeahdongcn merged 33983057 into master 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone