huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-12 04:44:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update server/text_generation_server/utils/import_utils.py

Browse Source 
Co-authored-by: Daniël de Kok <me@github.danieldk.eu>
This commit is contained in:
Wang, Yi 2024-06-14 08:48:39 +08:00 committed by GitHub
parent b0c0be48cf
commit 7396248379
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/utils/import_utils.py
View File

@ -21,7 +21,7 @@ def get_cuda_free_memory(device, memory_fraction):
def get_xpu_free_memory(device, memory_fraction): def get_xpu_free_memory(device, memory_fraction):
total_memory = torch.xpu.get_device_properties(device).total_memory total_memory = torch.xpu.get_device_properties(device).total_memory
device_id = str(device)[4] device_id = device.index
query = f"xpu-smi dump -d {device_id} -m 18 -n 1" query = f"xpu-smi dump -d {device_id} -m 18 -n 1"
output = subprocess.check_output(query.split()).decode("utf-8").split("\n") output = subprocess.check_output(query.split()).decode("utf-8").split("\n")
used_memory = float(output[1].split(",")[-1]) * 1024 * 1024 used_memory = float(output[1].split(",")[-1]) * 1024 * 1024