Skip to content

Actions: ggml-org/llama.cpp

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
69,966 workflow run results
69,966 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

improve CUDA cpy memory bandwidth when copying transposed tensor
Pull Request Labeler #18522: Pull request #16841 synchronize by bssrdf
4h 12m 19s
vulkan: fuse mul_mat+add and mul_mat_id+add_id
Pull Request Labeler #18521: Pull request #16868 synchronize by jeffbolznv
4h 12m 39s
vulkan: fix shmem overrun in mmq id shader
Pull Request Labeler #18520: Pull request #16873 synchronize by 0cc4m
4h 12m 4s
vulkan: fix shmem overrun in mmq id shader
Pull Request Labeler #18519: Pull request #16873 opened by 0cc4m
3h 14m 31s