llama.cpp
CUDA: add bf16 and f32 support to cublas_mul_mat_batched
#14361

Merged

CUDA: add bf16 and f32 support to cublas_mul_mat_batched #14361

am17an merged 4 commits into ggml-org:master from am17an:add_bp16_fp32_to_cublas_batched

am17an marked this pull request as ready for review 1 year ago

am17an requested a review from

JohannesGaessler 1 year ago

github-actions added testing

github-actions added Nvidia GPU

github-actions added ggml

am17an force pushed 1 year ago

JohannesGaessler commented on 2025-06-24

am17an force pushed 1 year ago

am17an requested a review from

JohannesGaessler 1 year ago

JohannesGaessler commented on 2025-06-25

am17an force pushed 1 year ago

am17an requested a review from

JohannesGaessler 1 year ago

JohannesGaessler approved these changes on 2025-06-25

CUDA: add bf16 and f32 support to cublas_mul_mat_batched

4887fa57

Review: add type traits and make function more generic

526fc4e0

Review: make check more explicit, add back comments, and fix formatting

c02cd2fc

Review: fix formatting, remove useless type conversion, fix naming fo…

2c4e42ed

am17an force pushed to 2c4e42ed 1 year ago

am17an merged 27208bf6 into master 1 year ago

am17an deleted the add_bp16_fp32_to_cublas_batched branch 347 days ago

Reviewers

JohannesGaessler

Assignees

No one assigned

Labels

testing Nvidia GPU ggml

Milestone

No milestone