sycl : Overcoming workaround for mmap() allocation on Windows (llama/13482)

* Remove mmap workaround on windows

After some testing I found that mmap is supported on windows and for
many GPUs on Linux. Therefore I remove the workaround for windows since
it is not necessary.

* Update llama-bench README

SYCL backend introduced a workaround that allows execution of
llama-bench also without specifying `--mmp 0` flag
This commit is contained in:
Nicolò Scipione 2025-05-20 02:54:43 +02:00 committed by Georgi Gerganov
parent 0b69f74e15
commit ee3f177cba

View File

@ -385,16 +385,17 @@ static void ggml_backend_sycl_buffer_set_tensor(ggml_backend_buffer_t buffer,
ggml_backend_sycl_buffer_context * ctx = ( ggml_backend_sycl_buffer_context *)buffer->context;
ggml_sycl_set_device(ctx->device);
auto stream = &(dpct::dev_mgr::instance().get_device(ctx->device).default_queue());
SYCL_CHECK(
CHECK_TRY_ERROR(dpct::dev_mgr::instance().get_device(ctx->device).queues_wait_and_throw()));
SYCL_CHECK(CHECK_TRY_ERROR(dpct::dev_mgr::instance().get_device(ctx->device).queues_wait_and_throw()));
#ifndef _WIN32
// Note: Use host buffer to save the data from mmap(), then copy to device. It's workaround for mmap() issue on PVC GPU.
// This function will be called during load model from disk. Use memory buffer replace dynamic won't save more time and brings potential memory leak risk here.
char * host_buf = (char *) malloc(size);
memcpy(host_buf, data, size);
SYCL_CHECK(
CHECK_TRY_ERROR((*stream).memcpy((char *)tensor->data + offset, host_buf, size)
.wait()));
SYCL_CHECK(CHECK_TRY_ERROR((*stream).memcpy((char *) tensor->data + offset, host_buf, size).wait()));
free(host_buf);
#else
SYCL_CHECK(CHECK_TRY_ERROR((*stream).memcpy((char *) tensor->data + offset, data, size).wait()));
#endif
}
catch (sycl::exception const &exc) {
std::cerr << exc.what() << "Exception caught at file:" << __FILE__