From b73aec7fa377ba6b28a4fc0c9e9f2907f3866371 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Wed, 29 Jan 2025 18:21:48 +0100 Subject: [PATCH] Hotfixing intel-cpu (not sure how it was working before). --- server/text_generation_server/models/__init__.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/server/text_generation_server/models/__init__.py b/server/text_generation_server/models/__init__.py index eb5a8de7..2d735227 100644 --- a/server/text_generation_server/models/__init__.py +++ b/server/text_generation_server/models/__init__.py @@ -180,7 +180,7 @@ except ImportError as e: if MAMBA_AVAILABLE: __all__.append(Mamba) -FLASH_TRANSFORMERS_BACKEND = True +FLASH_TRANSFORMERS_BACKEND = torch.cuda.is_available() try: from text_generation_server.models.transformers_flash_causal_lm import ( TransformersFlashCausalLM,