ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

hip : Add hipGraph and VMM support to ROCM (#11362)

Browse source 
* Add hipGraph support

* Enable VMM on rocm
This commit is contained in:
uvos 2025-01-25 00:02:23 +01:00 • committed by GitHub
parent c5d9effb49
commit 5f0db9522f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 92 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ggml/CMakeLists.txt
View file

@ -154,6 +154,7 @@ option(GGML_CUDA_FA_ALL_QUANTS "ggml: compile all quants for FlashA
option(GGML_CUDA_GRAPHS "ggml: use CUDA graphs (llama.cpp only)" ${GGML_CUDA_GRAPHS_DEFAULT})
option(GGML_HIP "ggml: use HIP" OFF)
option(GGML_HIP_GRAPHS "ggml: use HIP graph, experimental, slow" OFF)
option(GGML_HIP_UMA "ggml: use HIP unified memory architecture" OFF)
option(GGML_VULKAN "ggml: use Vulkan" OFF)
option(GGML_VULKAN_CHECK_RESULTS "ggml: run Vulkan op checks" OFF)