CUDA: remove -sm row, refactor cuBLAS (#24216)
* CUDA: remove -sm row, refactor cuBLAS * fix CDNA + BF16 logic * fix bad return * fix src0 strides, contiguous requirements * fix GGML_CUDA_FORCE_CUBLAS * fix casts to BF16
This commit is contained in:
@@ -953,6 +953,8 @@ static buft_list_t make_gpu_buft_list(ggml_backend_dev_t dev, llama_split_mode s
|
||||
if (buft != nullptr) {
|
||||
buft_list.emplace_back(dev, buft);
|
||||
}
|
||||
} else {
|
||||
throw std::runtime_error(format("device %s does not support split buffers", ggml_backend_dev_name(dev)));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user