huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-06-19 15:52:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

delete optimum.habana import

Browse Source 
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
This commit is contained in:
Wang, Yi A 2025-06-12 22:42:10 -07:00
parent 1e56e5fe5c
commit dbec20f98f
1 changed files with 14 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
backends/gaudi/server/text_generation_server/utils/debug.py
View File

@ -4,8 +4,8 @@ import os
import glob import glob
import time import time
from optimum.habana.utils import to_gb_rounded
import habana_frameworks.torch as htorch import habana_frameworks.torch as htorch
import numpy as np
START_TS = None START_TS = None
DBG_TRACE_FILENAME = os.environ.get("DBG_TRACE_FILENAME") DBG_TRACE_FILENAME = os.environ.get("DBG_TRACE_FILENAME")
@ -14,6 +14,19 @@ if "GRAPH_VISUALIZATION" in os.environ:
os.remove(f) os.remove(f)
def to_gb_rounded(mem: float) -> float:
"""
Rounds and converts to GB.
Args:
mem (float): memory in bytes
Returns:
float: memory in GB rounded to the second decimal
"""
return np.round(mem / 1024**3, 2)
def count_hpu_graphs(): def count_hpu_graphs():
return len(glob.glob(".graph_dumps/*PreGraph*")) return len(glob.glob(".graph_dumps/*PreGraph*"))