Compare commits

..

2 Commits

Author SHA1 Message Date
Akarshan Biswas 8b69686136 SYCL: fix rms_norm_mul_add for tensor dim not a multiple of sg_size (#15592)
The original implementation unconditionally returned true for this operation, leading to a failure when the tensor's first dimension (ne[0]) was not a multiple of WARP_SIZE. This caused an GGML_ASSERT(ncols % WARP_SIZE == 0) failure in ggml-sycl/norm.cpp.

This change updates the ggml_backend_sycl_device_supports_op check to correctly return true for GGML_OP_RMS_NORM only when the first dimension of the tensor is a multiple of WARP_SIZE, ensuring the operation can be performed without error.
2025-08-27 00:27:49 +05:30
fidoriel 8ce3ff1d91 mtmd : fix mtmd ios build (#15579) 2025-08-26 20:05:50 +02:00
2 changed files with 5 additions and 2 deletions
+2 -1
View File
@@ -4364,11 +4364,12 @@ static bool ggml_backend_sycl_device_supports_op(ggml_backend_dev_t dev, const g
return (op->type == GGML_TYPE_F32 && op->src[0]->type == GGML_TYPE_F32) && (op->type == op->src[0]->type);
#endif
case GGML_OP_NORM:
case GGML_OP_RMS_NORM:
return true;
case GGML_OP_L2_NORM:
case GGML_OP_GROUP_NORM:
return ggml_is_contiguous(op->src[0]);
case GGML_OP_RMS_NORM:
return ((op->src[0]->ne[0] % WARP_SIZE) == 0);
case GGML_OP_SCALE:
return true;
case GGML_OP_CONT:
+3 -1
View File
@@ -55,6 +55,8 @@ add_executable(llama-qwen2vl-cli deprecation-warning.cpp)
set(TARGET llama-mtmd-cli)
add_executable (${TARGET} mtmd-cli.cpp)
set_target_properties (${TARGET} PROPERTIES OUTPUT_NAME llama-mtmd-cli)
install (TARGETS ${TARGET} RUNTIME)
if(NOT CMAKE_SYSTEM_NAME STREQUAL "iOS")
install(TARGETS ${TARGET} RUNTIME)
endif()
target_link_libraries (${TARGET} PRIVATE common mtmd Threads::Threads)
target_compile_features(${TARGET} PRIVATE cxx_std_17)