From bf974da5cd248ad52d15b62bb1636c00a204bd42 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Sun, 5 Jul 2026 00:44:18 +0000 Subject: [PATCH] Cover olmo_hybrid in the gated-deltanet fla advisory --- unsloth/models/loader.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unsloth/models/loader.py b/unsloth/models/loader.py index cd4c13aff5..ba23197861 100644 --- a/unsloth/models/loader.py +++ b/unsloth/models/loader.py @@ -209,7 +209,7 @@ DISABLE_COMPILE_MODEL_NAMES = [ # Architectures with gated-deltanet (linear attention) layers. Unsloth bundles the # flash-linear-attention Triton kernels (unsloth_zoo/_vendored/fla), so no install is # needed; transformers uses the much slower pure PyTorch path only when they can't be enabled. -FLA_MODEL_TYPE_PREFIXES = ("qwen3_next", "qwen3_5", "kimi_linear") +FLA_MODEL_TYPE_PREFIXES = ("qwen3_next", "qwen3_5", "kimi_linear", "olmo_hybrid") _fla_advised = False