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

fix: cleanup ruff lints

This commit is contained in:
David Holtz 2024-10-09 19:27:23 +00:00
parent 247033b45f
commit 541c476492
1 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
server/tests/utils/test_kv_cache.py
View File

@ -1,6 +1,4 @@
import torch import torch
import pytest
from text_generation_server.models.globals import ATTENTION, BLOCK_SIZE
from text_generation_server.utils.import_utils import SYSTEM from text_generation_server.utils.import_utils import SYSTEM
# only include this import when CUDA is available # only include this import when CUDA is available
@ -18,7 +16,7 @@ def kvcache_memory():
current_memory = torch.cuda.memory_allocated(device) current_memory = torch.cuda.memory_allocated(device)
kv_cache = [ _kv_cache = [
KVCache( KVCache(
num_blocks=num_blocks, num_blocks=num_blocks,
num_heads=num_kv_heads, num_heads=num_kv_heads,