From 0eea83be44f0edbd934394b17602fe48ddc267cc Mon Sep 17 00:00:00 2001 From: fxmarty <9808326+fxmarty@users.noreply.github.com> Date: Wed, 8 Nov 2023 19:07:58 +0900 Subject: [PATCH] Update server/text_generation_server/models/custom_modeling/flash_mistral_modeling.py --- .../models/custom_modeling/flash_mistral_modeling.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/server/text_generation_server/models/custom_modeling/flash_mistral_modeling.py b/server/text_generation_server/models/custom_modeling/flash_mistral_modeling.py index e34a2b1c..7d91722e 100644 --- a/server/text_generation_server/models/custom_modeling/flash_mistral_modeling.py +++ b/server/text_generation_server/models/custom_modeling/flash_mistral_modeling.py @@ -43,7 +43,7 @@ if IS_CUDA_SYSTEM: elif IS_ROCM_SYSTEM: from vllm import layernorm_ops -if not HAS_FLASH_ATTN_V2_ROCM and not HAS_FLASH_ATTN_V2_ROCM: +if not HAS_FLASH_ATTN_V2_CUDA and not HAS_FLASH_ATTN_V2_ROCM: raise ImportError("Mistral model requires flash attn v2")