ipfans
ipfans
@trim21 it's a concurrcy bug that not easy to repoduce all the time. It could be happen when your program in high loads.
@trim21 I think the first example could reproduce this issue. But you may need try it multiple times
Oh, of course. Welcome to PR
Can you end a pull request for this issue?
@zhuwenxing This PR is not related to PDM tool itself. [src/openllm/venv.py](https://github.com/bentoml/OpenLLM/pull/1054/files#diff-456e3196cb173e8694b7827080eddaca02615e61b96a83f834509c880647f356)
Organization/Company: EKEYNOW Pte. Ltd. Website: https://www.ekeynow.com/ Country: Singapore Contact: [email protected] Usage scenario: Moving to Dapr to build large scale SaaS applications. Status: In Development
@zylo117 I want to double check, because if there is a CUDA version mismatch, the compilation error will be(build with CUDA_HOME to 12.1): ``` File "/home/user/proj/.venv/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 417, in _check_cuda_version...
@zylo117 oh, you are right. I have success after downgrade pytorch==2.1.2
@pojntfx Not yet, I just run a demo transcrption. I think it can be a demo html with all tags go-app supported. I will try this later.
@LouisAldorio I apologize for any inconvenience caused by the gap between the current version and the latest API. This version does not include some of the new API definitions.