mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-10-29 22:20:15 +01:00
6f1d9d71f4
* Fix Docker ROCM builds, use AMDGPU_TARGETS instead of GPU_TARGETS * Set ROCM_DOCKER_ARCH as string due it incorrectly build and cause OOM exit code |
||
---|---|---|
.. | ||
ISSUE_TEMPLATE | ||
workflows | ||
labeler.yml | ||
pull_request_template.md |