Skip to content

Update custom_model.py #227

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update custom_model.py #227

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 11 additions & 2 deletions magic_pdf/model/custom_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -199,7 +199,11 @@ def __init__(self, model_path):
self.gen_config = SamplingParams(max_tokens=4096,temperature=0,repetition_penalty=1.05)

def _auto_gpu_mem_ratio(self, ratio):
mem_free, mem_total = torch.cuda.mem_get_info()
if torch.cuda.is_available():
mem_free, mem_total = torch.cuda.mem_get_info()
else:
import torch_npu
mem_free, mem_total = torch_npu.npu.mem_get_info()
ratio = ratio * mem_free / mem_total
return ratio

Expand Down Expand Up @@ -905,7 +909,12 @@ def __init__(self, model_path, max_batch_size=64, queue_timeout=0.1, max_queue_s
logger.info(f"Max batch size: {max_batch_size}, Queue timeout: {queue_timeout}s")

def _auto_gpu_mem_ratio(self, ratio):
mem_free, mem_total = torch.cuda.mem_get_info()
if torch.cuda.is_available():
mem_free, mem_total = torch.cuda.mem_get_info()
else:
import torch_npu
# npu上ratio设置0.6比较合适
mem_free, mem_total = torch_npu.npu.mem_get_info()
ratio = ratio * mem_free / mem_total
return ratio

Expand Down