huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update server/text_generation_server/models/custom_modeling/flash_mistral_modeling.py

Browse Source
This commit is contained in:
fxmarty 2023-11-08 19:07:58 +09:00 committed by GitHub
parent 891fe74099
commit 0eea83be44
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/models/custom_modeling/flash_mistral_modeling.py
View File

@ -43,7 +43,7 @@ if IS_CUDA_SYSTEM:
elif IS_ROCM_SYSTEM: elif IS_ROCM_SYSTEM:
from vllm import layernorm_ops 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") raise ImportError("Mistral model requires flash attn v2")