llama.cpp
cuda: respect src1 GGML_PREC_F32 in F32/F16 mul_mat
#31844

Open

cuda: respect src1 GGML_PREC_F32 in F32/F16 mul_mat #31844

ServeurpersoCom wants to merge 2 commits into master from pascal/cuda-mul-mat-prec-src1

metal: respect src1 GGML_PREC_F32 in F32/F16 mul_mm

62747eb2

cuda: respect src1 GGML_PREC_F32 in F32/F16 mul_mat

f3115198

ServeurpersoCom requested a review from

ggerganov 8 days ago

ServeurpersoCom requested a review 8 days ago

github-actions added testing

github-actions added ggml

github-actions added Apple Metal

github-actions added CUDA

ggerganov marked this pull request as draft 8 days ago

Reviewers

ggerganov

Assignees

No one assigned

Labels

testing ggml Apple Metal CUDA

Milestone

No milestone