From 7dce7e45fa83ad63191720bab067ccf629dcb81a Mon Sep 17 00:00:00 2001 From: leejet Date: Sun, 1 Feb 2026 21:35:32 +0800 Subject: [PATCH] update docs --- examples/cli/README.md | 3 ++- examples/server/README.md | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/examples/cli/README.md b/examples/cli/README.md index d6c36b8..78f8821 100644 --- a/examples/cli/README.md +++ b/examples/cli/README.md @@ -52,7 +52,8 @@ Context Options: --control-net-cpu keep controlnet in cpu (for low vram) --clip-on-cpu keep clip in cpu (for low vram) --vae-on-cpu keep vae in cpu (for low vram) - --diffusion-fa use flash attention in the diffusion model + --fa use flash attention + --diffusion-fa use flash attention in the diffusion model only --diffusion-conv-direct use ggml_conv2d_direct in the diffusion model --vae-conv-direct use ggml_conv2d_direct in the vae model --circular enable circular padding for convolutions diff --git a/examples/server/README.md b/examples/server/README.md index 354075c..8a2f2e9 100644 --- a/examples/server/README.md +++ b/examples/server/README.md @@ -44,7 +44,8 @@ Context Options: --clip-on-cpu keep clip in cpu (for low vram) --vae-on-cpu keep vae in cpu (for low vram) --mmap whether to memory-map model - --diffusion-fa use flash attention in the diffusion model + --fa use flash attention + --diffusion-fa use flash attention in the diffusion model only --diffusion-conv-direct use ggml_conv2d_direct in the diffusion model --vae-conv-direct use ggml_conv2d_direct in the vae model --circular enable circular padding for convolutions