HIP: force max threads per block to be 1024 (ggml-org#11621)

Some old/vendor forked version of llvm still use 256. Explicitly set it to 1024 to align with upstream llvm. Signed-off-by: fxzjshm <fxzjshm@163.com>
zhouwg · Feb 4, 2025 · 3ec9fd4 · 3ec9fd4
1 parent 3962fc1
commit 3ec9fd4
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/ggml/src/ggml-hip/CMakeLists.txt b/ggml/src/ggml-hip/CMakeLists.txt
@@ -46,6 +46,9 @@ endif()
 
 message(STATUS "HIP and hipBLAS found")
 
+# Workaround old compilers
+set(CMAKE_HIP_FLAGS "${CMAKE_HIP_FLAGS} --gpu-max-threads-per-block=1024")
+
 file(GLOB   GGML_HEADERS_ROCM "../ggml-cuda/*.cuh")
 list(APPEND GGML_HEADERS_ROCM "../../include/ggml-cuda.h")