sync: update ggml to fix large image generation with SYCL backend (#380)

* turn off fast-math on host in SYCL backend

Signed-off-by: zhentaoyu <[email protected]>

* update ggml for sync some sycl ops

Signed-off-by: zhentaoyu <[email protected]>

* update sycl readme and ggml

Signed-off-by: zhentaoyu <[email protected]>

---------

Signed-off-by: zhentaoyu <[email protected]>

fix: fix clip tokenizer (#383)

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

fix: improve VAE tiling (#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 <[email protected]>

* remove the now unused lerp function

---------

Co-authored-by: stduhpf <[email protected]>

feat: add exponential scheduler (#346)

* feat: added exponential scheduler

* updated README

* improved exponential formatting

---------

Co-authored-by: leejet <[email protected]>

feat: add ipndm and ipndm_v samplers (#344)

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

…351)

fix: add enum type to sd_type_t (#293)

feat: add GITS scheduler (#343)

feat: add vulkan backend support (#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 <[email protected]>
Co-authored-by: Oleg Skutte <[email protected]>
Co-authored-by: leejet <[email protected]>