ftobler/llama
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

whitespace

Browse Source
This commit is contained in:
Florin Tobler
2025-01-13 23:32:54 +01:00
parent ef789375c8
commit 3218e7eb63
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
inference_profile_test.py
View File

@@ -10,7 +10,7 @@ def empty_cuda():
while True: while True:
gc.collect() gc.collect()
torch.cuda.empty_cache() torch.cuda.empty_cache()
time.sleep(0.5) time.sleep(0.5)
vram = nvidia_smi.get_gpu_stats()["memory_used"] vram = nvidia_smi.get_gpu_stats()["memory_used"]
print("vram: %d MB" % vram) print("vram: %d MB" % vram)
if vram < 200: if vram < 200: