]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
ggml-cuda: Adding support for unified memory (#8035)
authormatteo <redacted>
Thu, 1 Aug 2024 21:28:28 +0000 (23:28 +0200)
committerGitHub <redacted>
Thu, 1 Aug 2024 21:28:28 +0000 (23:28 +0200)
commitafbb4c1322a747d2a7b4bf67c868148f8afcc6c8
treef1654a9ac6be5b66f1d94694df0083f063f5ee8c
parentb7a08fd5e0e7c898c68d1743066ea495202d9608
ggml-cuda: Adding support for unified memory (#8035)

* Adding support for unified memory

* adding again the documentation about unified memory

* refactoring: Moved the unified memory code in the correct location.

* Fixed compilation error when using hipblas

* cleaning up the documentation

* Updating the documentation

Co-authored-by: Johannes Gäßler <redacted>
* adding one more case where the PR should not be enabled

---------

Co-authored-by: matteo serva <redacted>
Co-authored-by: Johannes Gäßler <redacted>
docs/build.md
ggml/src/ggml-cuda.cu