From b8d843e7db80479d20e2ebf882c62685703492a8 Mon Sep 17 00:00:00 2001 From: deepbeepmeep Date: Fri, 8 Aug 2025 23:20:00 +0200 Subject: [PATCH] updated releases notes --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 3355b31..42fc5f6 100644 --- a/README.md +++ b/README.md @@ -25,7 +25,7 @@ Ever wondered what impact not using Guidance has on a model that expects it ? Ju As Qwen is not so picky after all I have added also quantized text encoder which reduces the RAM requirements of Qwen by 10 GB (the text encoder quantized version produced garbage before) -Hopefully this new release solves as well the Sage/Sage2 blacscreen on some GPUs. +Unfortunately still the Sage bug for older GPU architectures. Added Sdpa fallback for these architectures. *7.73 update: still Sage / Sage2 bug for GPUs before RTX40xx. I have added a detection mechanism that forces Sdpa attention if that's the case*