CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-16 11:27:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

cuda : enable CUDA Graph on CUDA Toolkit < 12.x (#12394)

Browse Source 
* Enable CUDA Graph on CTK < 12.x

`cudaGraphExecUpdate` API was changed on 12.x. For this reason CUDA graph support was disabled on older CUDA toolkit. This change enables CUDA support in CTK version < 12.x by using older API if CTK < 12.x.

* Fix compilation errors with MUSA

* Disable CUDA Graph for MUSA
This commit is contained in:
Gaurav Garg
2025-03-17 23:55:13 +05:30
committed by GitHub
parent 01e8f2138b
commit b1b132efcb
5 changed files with 11 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-musa/CMakeLists.txt
View File

@@ -67,10 +67,6 @@ if (MUSAToolkit_FOUND)
add_compile_definitions(GGML_USE_MUSA)
add_compile_definitions(GGML_CUDA_PEER_MAX_BATCH_SIZE=${GGML_CUDA_PEER_MAX_BATCH_SIZE})
if (GGML_CUDA_GRAPHS)
add_compile_definitions(GGML_CUDA_USE_GRAPHS)
endif()
if (GGML_CUDA_FORCE_MMQ)
add_compile_definitions(GGML_CUDA_FORCE_MMQ)
endif()