From 715a68bee7bd467460a9eee758f03975a01408e6 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Thu, 18 Jun 2026 14:16:56 -0700 Subject: [PATCH] feat(comfyui): native --use-sage-attention (node path dead on 0.24.1) ComfyUI 0.24.1 added native attention selection; the node-based BlehGlobalSageAttention errors "does not support the new ComfyUI attention changes". Add --use-sage-attention to COMFY_CMDLINE_EXTRA so the in-image sageattention v2.2.0 sm_86 build (rebuilt vs pinned torch 2.12.1) binds via the native path. OOM flags preserved. Deployed to irv-ml1 + recreated; log confirms "Using sage attention", container healthy, serving 200. (comfy-dev request, thread 01KVE89T2DKC) --- stacks/comfyui/compose.yaml | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/stacks/comfyui/compose.yaml b/stacks/comfyui/compose.yaml index 44a455a..4914bdb 100644 --- a/stacks/comfyui/compose.yaml +++ b/stacks/comfyui/compose.yaml @@ -51,7 +51,12 @@ services: # (~8.7 GB) instead of upcasting the fp8 file to fp16 (~16 GB). Matches # the box's Ampere-fp8 posture; the encoder runs once per gen so the # upcast-on-compute cost is negligible. - - COMFY_CMDLINE_EXTRA=--disable-cuda-malloc --fp8_e4m3fn-text-enc + # --use-sage-attention — 0.24.1's NATIVE attention selection (the node-based + # BlehGlobalSageAttention is dead on 0.24.1: "does not support the new + # ComfyUI attention changes"). Binds the in-image sageattention v2.2.0 + # sm_86 build (rebuilt against the pinned torch 2.12.1). Global speedup + # across Flux/SDXL/Wan (comfy-dev benchmarking, 2026-06-18). + - COMFY_CMDLINE_EXTRA=--disable-cuda-malloc --fp8_e4m3fn-text-enc --use-sage-attention volumes: - ${COMFYUI_BASEDIR}:/basedir # models/ overlaid from storetank. The ~325 GB model tree was migrated