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

del model after test (#9504)

Browse source
This commit is contained in:
WeiguangHan 2023-11-21 18:41:50 +08:00 committed by GitHub
parent 076d106ef5
commit c2aeb4d1e8
1 changed files with 3 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
python/llm/dev/benchmark/all-in-one/run.py
View file

@ -394,6 +394,7 @@ def run_transformer_int4_gpu(repo_id,
actual_in_len, actual_out_len]) actual_in_len, actual_out_len])
except RuntimeError: except RuntimeError:
pass pass
del model
torch.xpu.empty_cache() torch.xpu.empty_cache()
return result return result
@ -473,6 +474,7 @@ def run_optimize_model_gpu(repo_id,
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]) actual_in_len, actual_out_len])
del model
torch.xpu.empty_cache() torch.xpu.empty_cache()
return result return result
@ -544,6 +546,7 @@ def run_ipex_fp16_gpu(repo_id,
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]) actual_in_len, actual_out_len])
del model
torch.xpu.empty_cache() torch.xpu.empty_cache()
return result return result