]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: cbaadc9)
Refactor Error Handling for CUDA (#6575)
authorNikolas <redacted>
Thu, 11 Apr 2024 19:56:29 +0000 (21:56 +0200)
committerGitHub <redacted>
Thu, 11 Apr 2024 19:56:29 +0000 (21:56 +0200)
commita474f50ebb3e10be3371562f75f3f573f1a86b5f
tree4e6af54d32a0b50dbfa5f1486e64615761e83d41tree
parentcbaadc92942c50aab599a9e4c163afc1f44f7c26commit | diff
Refactor Error Handling for CUDA (#6575)

* Refactor Error Handling for CUDA

Add guidance for setting CUDA_DOCKER_ARCH to match GPU compute capability for CUDA versions < 11.7. Include link to NVIDIA's CUDA GPUs documentation for compute capability reference.

* Update Makefile

Improved wording

Co-authored-by: Johannes Gäßler <redacted>
---------

Co-authored-by: Johannes Gäßler <redacted>
Makefile diff | blob | history
Packaging of ggml-org/llama.cpp