Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

hotfix: ipex fails since cuda moe kernel is not supported (#2532) 

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
This commit is contained in:
Wang, Yi 2024-09-20 16:02:55 +08:00 committed by GitHub
parent abd24dd385
commit f478aa77ad
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
server/text_generation_server/models/custom_modeling/flash_deepseek_v2_modeling.py
View File

@ -15,7 +15,6 @@
from typing import List, Optional, Tuple from typing import List, Optional, Tuple
from moe_kernels.fused_moe import grouped_topk
import torch import torch
import torch.distributed import torch.distributed
from text_generation_server.layers import ( from text_generation_server.layers import (
@ -41,6 +40,9 @@ from torch import nn
from transformers.activations import ACT2FN from transformers.activations import ACT2FN
from transformers.configuration_utils import PretrainedConfig from transformers.configuration_utils import PretrainedConfig
if SYSTEM != "ipex":
from moe_kernels.fused_moe import grouped_topk
if SYSTEM == "rocm": if SYSTEM == "rocm":
try: try:
from vllm import _custom_C from vllm import _custom_C