llama.cpp
backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels
#9921

Merged

backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels #9921

slaren merged 8 commits into ggml-org:master from chaxu01:feature/online-flow

github-actions added examples

github-actions added ggml

chaxu01 force pushed 1 year ago

chaxu01 force pushed 1 year ago

backend-cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels

647eb316

refactor add new buffer type for online flow

b632bf0f

retain the tensor type as Q4_0

5947d72c

add check for tensor dimensions

871036d2

chaxu01 force pushed to 871036d2 1 year ago

rebased onto commit a0a4646

76d89758

fix build error

2268ce0c

slaren commented on 2024-11-08

Update ggml/CMakeLists.txt

74d660ab

Merge remote-tracking branch 'origin/master' into feature/online-flow

749a9e5e

slaren force pushed to 749a9e5e 1 year ago

slaren approved these changes on 2024-11-14

slaren merged 1607a5e5 into master 1 year ago

chaxu01 deleted the feature/online-flow branch 115 days ago

Reviewers

slaren

Assignees

No one assigned

Labels

examples ggml

Milestone

No milestone