sync: update ggml to fix large image generation with SYCL backend (le…

…ejet#380)

* turn off fast-math on host in SYCL backend

Signed-off-by: zhentaoyu <zhentao.yu@intel.com>

* update ggml for sync some sycl ops

Signed-off-by: zhentaoyu <zhentao.yu@intel.com>

* update sycl readme and ggml

Signed-off-by: zhentaoyu <zhentao.yu@intel.com>

---------

Signed-off-by: zhentaoyu <zhentao.yu@intel.com>

fix: fix clip tokenizer (leejet#383)

fix: add some missing cli args to usage (leejet#363)

fix: improve VAE tiling (leejet#372)

* fix and improve: VAE tiling
- properly handle the upper left corner interpolating both x and y
- refactor out lerp
- use smootherstep to preserve more detail and spend less area blending

* actually fix vae tile merging

Co-authored-by: stduhpf <stephduh@live.fr>

* remove the now unused lerp function

---------

Co-authored-by: stduhpf <stephduh@live.fr>

feat: add exponential scheduler (leejet#346)

* feat: added exponential scheduler

* updated README

* improved exponential formatting

---------

Co-authored-by: leejet <leejet714@gmail.com>

feat: add ipndm and ipndm_v samplers (leejet#344)

feat: add vulkan backend support (leejet#291)

* Fix includes and init vulkan the same as llama.cpp

* Add Windows Vulkan CI

* Updated ggml submodule

* support epsilon as a parameter for ggml_group_norm

---------

Co-authored-by: Cloudwalk <cloudwalk@icculus.org>
Co-authored-by: Oleg Skutte <00.00.oleg.00.00@gmail.com>
Co-authored-by: leejet <leejet714@gmail.com>

fix: fix some typos (leejet#361)

fix: add enum type to sd_type_t (leejet#293)

fix: resolve naming conflict while llama.cpp and sd.cpp both build (l…

…eejet#351)