llama.cpp
cpu: introduce chunking for repack matmuls and enable matmul-id chunking
#16833

Merged

cpu: introduce chunking for repack matmuls and enable matmul-id chunking #16833

max-krasnyansky merged 1 commit into ggml-org:master from qualcomm:repack-matmul-chunking

cpu: introduce chunking for repack matmuls and enable matmul-id chunk…

34924412

max-krasnyansky requested a review from

ggerganov 52 days ago

max-krasnyansky requested a review from

slaren 52 days ago

github-actions added ggml

slaren approved these changes on 2025-10-30

max-krasnyansky merged 517b7170 into master 51 days ago

max-krasnyansky deleted the repack-matmul-chunking branch 51 days ago

Reviewers

slaren

ggerganov

Assignees

No one assigned

Labels

ggml

Milestone

No milestone