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

Fix missing make target: https://github.com/huggingface/text-generation-inference/issues/1397

Browse Source
This commit is contained in:
deepily 2024-01-05 17:29:35 -05:00
parent 630800eed3
commit 716fe00d92
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
server/text_generation_server/utils/flash_attn.py
View File

@ -23,10 +23,15 @@ try:
try: try:
import flash_attn_2_cuda import flash_attn_2_cuda
except ImportError: except ImportError:
architecture_suffix = ""
if IS_CUDA_SYSTEM:
architecture_suffix = "-cuda"
elif IS_ROCM_SYSTEM:
architecture_suffix = "-rocm"
raise ImportError( raise ImportError(
"Flash Attention V2 is not installed.\n" "Flash Attention V2 is not installed.\n"
"Use the official Docker image (ghcr.io/huggingface/text-generation-inference:latest) " "Use the official Docker image (ghcr.io/huggingface/text-generation-inference:latest) "
"or install flash attention v2 with `cd server && make install install-flash-attention-v2`" f"or install flash attention v2 with `cd server && make install install-flash-attention-v2{architecture_suffix}`"
) )
if not (is_sm8x or is_sm90): if not (is_sm8x or is_sm90):
raise ImportError( raise ImportError(