cbensimon HF staff commited on
Commit
496445e
1 Parent(s): 7aec4dc

Reduce ZeroGPU requested duration

Browse files

Generation took 107s on my side (requesting too much time will force users to (un-necessary) wait a lot for their quotas to recharge)

Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -30,7 +30,7 @@ import glob
30
 
31
  subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
32
 
33
- @spaces.GPU(duration=500)
34
  def run_inference(prompt_text):
35
  repo_id = "hpcai-tech/Open-Sora"
36
 
 
30
 
31
  subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
32
 
33
+ @spaces.GPU(duration=200)
34
  def run_inference(prompt_text):
35
  repo_id = "hpcai-tech/Open-Sora"
36