llama.cpp
llama : disable graph reuse when contexts share memory under SPLIT_MODE_TENSOR
#24549

Open

llama : disable graph reuse when contexts share memory under SPLIT_MODE_TENSOR #24549

nycdubliner wants to merge 1 commit into ggml-org:master from nycdubliner:fix/graph-reuse-shared-kv-tensor-split

nycdubliner requested a review from

ggerganov 1 day ago

nycdubliner marked this pull request as draft 1 day ago

llama : disable graph reuse when contexts share memory under SPLIT_MO…

9432df67

nycdubliner force pushed from e0ba2c88 to 9432df67 1 day ago

nycdubliner marked this pull request as ready for review 1 day ago

Reviewers

ggerganov

Assignees

No one assigned

Labels

None yet

Milestone

No milestone