ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Fix run.py run_ipex_fp16_gpu (#11361)

Browse source 
* fix a bug on run.py

* Update run.py

fixed the format problem

---------

Co-authored-by: sgwhat <ge.song@intel.com>
This commit is contained in:
RyuKosei 2024-06-20 10:29:32 +08:00 committed by GitHub
parent b2f62a8561
commit 05a8d051f6
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
python/llm/dev/benchmark/all-in-one/run.py
View file

@ -698,7 +698,7 @@ def run_ipex_fp16_gpu(repo_id,
print(output[0]) print(output[0])
if i >= warm_up: if i >= warm_up:
result[in_out].append([model.first_cost, model.rest_cost_mean, model.encoder_time, result[in_out].append([model.first_cost, model.rest_cost_mean, model.encoder_time,
actual_in_len, actual_out_len, load_time]) actual_in_len, actual_out_len, load_time, model.peak_memory])
del model del model
torch.xpu.empty_cache() torch.xpu.empty_cache()
return result return result