Skip to content

ggml-cuda: avoid direct ROCm_Host compute on HIP integrated GPUs (port of ggml-org#25863) - #158

Open
danielhanchen wants to merge 2 commits into
masterfrom
port/25863-hip-integrated-host-buft
Open

ggml-cuda: avoid direct ROCm_Host compute on HIP integrated GPUs (port of ggml-org#25863)#158
danielhanchen wants to merge 2 commits into
masterfrom
port/25863-hip-integrated-host-buft

Merge b11609: route the host buffer check through ggml_cuda_pinned_me…

fb9b946
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs