Skip to content
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.

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

Qwen2.5推理报错 #64

Open
zsy-v opened this issue Dec 12, 2024 · 1 comment
Open

Qwen2.5推理报错 #64

zsy-v opened this issue Dec 12, 2024 · 1 comment

Comments

@zsy-v
Copy link

zsy-v commented Dec 12, 2024

python3 pipeline.py --model_path qwen2.5-1.5b_int4_seq512_1dev.bmodel --tokenizer_path ../support/token_config/ --devid 0 --generation_mode greedy
Load ../support/token_config/ ...
Device [ 0 ] loading ....
Model[qwen2.5-1.5b_int4_seq512_1dev.bmodel] loading ....
Done!

Load Time: 21.452 s

=================================================================

  1. If you want to quit, please enter one of [q, quit, exit]
  2. To create a new chat session, please enter one of [clear, new]
    =================================================================

Question: nihao

Answer: [bmlib_runtime][error] bmdev handle sync api failed, ioclt ret = -1 455
python3: /data/zhousy26/hello/python_demo/../support/include/utils.h:437: void empty(bm_context*&, bm_device_mem_t&): Assertion `BM_SUCCESS == ret' failed.
Aborted

这个是发生了什么问题?

@chuxiaoyi2023
Copy link
Collaborator

bm-smi康康呢,像是环境问题

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants