huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: removed unused import.

Browse Source
This commit is contained in:
Nilabhra 2024-05-14 11:00:45 +04:00
parent 56ed686942
commit 011887f15c
1 changed files with 6 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
server/text_generation_server/models/custom_modeling/flash_llama_modeling.py
View File

@ -18,25 +18,22 @@
# See the License for the specific language governing permissions and # See the License for the specific language governing permissions and
# limitations under the License. # limitations under the License.
from typing import List, Optional, Tuple
import torch import torch
import torch.distributed import torch.distributed
from torch import nn from torch import nn
from transformers.activations import ACT2FN from transformers.activations import ACT2FN
from typing import Optional, List, Tuple
from text_generation_server.utils import paged_attention, flash_attn
from text_generation_server.layers import ( from text_generation_server.layers import (
TensorParallelRowLinear, SpeculativeHead,
TensorParallelColumnLinear, TensorParallelColumnLinear,
TensorParallelEmbedding, TensorParallelEmbedding,
SpeculativeHead, TensorParallelRowLinear,
get_linear,
) )
from text_generation_server.layers.layernorm import FastRMSNorm
from text_generation_server.layers.rotary import PositionRotaryEmbedding from text_generation_server.layers.rotary import PositionRotaryEmbedding
from text_generation_server.layers.layernorm import ( from text_generation_server.utils import flash_attn, paged_attention
FastRMSNorm,
)
def load_attention(config, prefix, weights): def load_attention(config, prefix, weights):