Daniel Hiltgen c3d321d405

llm: Remove GGML_CUDA_NO_PEER_COPY for ROCm (#7174) ...

This workaround logic in llama.cpp is causing crashes for users with less system memory than VRAM.

2024-10-12 09:56:49 -07:00

..

gen_common.sh

Fix build leakages (#7141)

2024-10-08 13:04:59 -07:00

gen_darwin.sh

Re-introduce the llama package (#5034)

2024-10-08 08:53:54 -07:00

gen_linux.sh

llm: Remove GGML_CUDA_NO_PEER_COPY for ROCm (#7174)

2024-10-12 09:56:49 -07:00

gen_windows.ps1

llm: Remove GGML_CUDA_NO_PEER_COPY for ROCm (#7174)

2024-10-12 09:56:49 -07:00

generate_darwin.go

…

generate_linux.go

…

generate_windows.go

…