master-6c88ad3

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

master-353ee93

fix: add enum type to sd_type_t (#293)

master-2d4a2f7

feat: add GITS scheduler (#343)

master-2027b16

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]>

master-0362cc4

fix: fix some typos (#361)

master-f5997a1

fix: do not force using f32 for some flux layers

This sometimes leads to worse result

master-8847114

fix: fix issue when applying lora

master-79c9fe9

feat: do not convert some tensors

master-5c561ea

feat: do not convert more flux tensors

master-1bdc767

feat: force using f32 for some layers