[SYCL]: Remove per-allocation Level Zero runtime checks (#23399)

* [SYCL] Centralize Level Zero detection in ggml_sycl_init

* use the same wording

* get back the warning

* [SYCL] Remove per-allocation getenv() for GGML_SYCL_ENABLE_LEVEL_ZERO

* bring back the comment

* move it up to make sure devices call the shots

* move the env detection early

* replace g_ggml_sycl_enable_level_zero with a direct call to .ext_oneapi_level_zero

* update the comment

* switch back to g_ggml_sycl_enable_level_zero with a sentinel

* remove the check

* Reduce the diff

* reword, move lower

* move things aroudn

* remove forward declaration if favor of a full replace

* pre-cache results of zeDeviceGetProperties

* put ggml_sycl_get_env back

* replace get_sycl_env with ggml_sycl_get_env

* add whitespace back

* Apply suggestion from @sanmai

ggml/src/ggml-sycl/common.hpp

@@ -225,6 +225,7 @@ struct sycl_device_info {
     int max_wg_per_cu; // max work groups per compute unit - refer to
                        // cudaOccupancyMaxActiveBlocksPerMultiprocessor
     bool    vmm;                // virtual memory support
+    bool    l0_discrete_gpu;    // Level Zero backend and not an integrated GPU
     size_t  vmm_granularity;    // granularity of virtual memory
     size_t  total_vram;
     sycl_hw_info hw_info;
@@ -644,6 +645,8 @@ constexpr size_t ceil_div(const size_t m, const size_t n) {
 
 bool gpu_has_xmx(sycl::device &dev);
 
+int ggml_sycl_get_env(const char *env_name, int default_val);
+
 template <int N, class T> std::string debug_get_array_str(const std::string & prefix, const T array[N]) {
     if (LIKELY(!g_ggml_sycl_debug)) {
         return "";