upstream-archive/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-09-29 01:18:05 -05:00
Code Issues Packages Projects Releases Wiki Activity

feat: add native CUDA SageAttention support (#2005)

Browse Source
This commit is contained in:
leejet
2026-09-21 01:16:59 +08:00
committed by GitHub
parent 15f335daa5
commit 187b2561ea
13 changed files with 176 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/common/common.cpp
+6
View File
@@ -618,6 +618,10 @@ ArgOptions SDContextParams::get_options() {
"--diffusion-fa",
"use flash attention in the diffusion model only",
true, &diffusion_flash_attn},
{"",
"--sage-attn",
"use native CUDA SageAttention in the diffusion model, with flash/default attention fallback",
true, &sage_attn},
{"",
"--diffusion-conv-direct",
"use ggml_conv2d_direct in the diffusion model",
@@ -938,6 +942,7 @@ std::string SDContextParams::to_string() const {
<< " vae_on_cpu: " << (vae_on_cpu ? "true" : "false") << ",\n"
<< " flash_attn: " << (flash_attn ? "true" : "false") << ",\n"
<< " diffusion_flash_attn: " << (diffusion_flash_attn ? "true" : "false") << ",\n"
<< " sage_attn: " << (sage_attn ? "true" : "false") << ",\n"
<< " linear_scale: " << linear_scale << ",\n"
<< " attn_scale: " << attn_scale << ",\n"
<< " diffusion_conv_direct: " << (diffusion_conv_direct ? "true" : "false") << ",\n"
@@ -995,6 +1000,7 @@ sd_ctx_params_t SDContextParams::to_sd_ctx_params_t(bool taesd_preview) {
sd_ctx_params.enable_mmap = enable_mmap;
sd_ctx_params.flash_attn = flash_attn;
sd_ctx_params.diffusion_flash_attn = diffusion_flash_attn;
sd_ctx_params.sage_attn = sage_attn;
sd_ctx_params.linear_scale = linear_scale;
sd_ctx_params.attn_scale = attn_scale;
sd_ctx_params.tae_preview_only = taesd_preview;