KrishnanPrash

Results 8 comments of KrishnanPrash

feat: Python Deployment of Triton Inference Server

> Are there any plans to make this part of the In-Process Python API? I think it would be nice if we could start the server using `python3 -m tritonserver.entrypoints.kserve.http...

feat: Python Deployment of Triton Inference Server

@GuanLuo Ready for review

python_backend pytorch example as_numpy() error

Hey @mauriciocm9 @flian2, Hopefully, [this PR](https://github.com/triton-inference-server/python_backend/pull/384) should resolve the issue you are experiencing allowing you to install `numpy 1.x` or `numpy 2.x` in your environment without any issues from the...

python_backend pytorch example as_numpy() error

Closing this issue due to inactivity. Please feel free to reopen if needed.

Does triton inference server support customers custom feature but do not need to modify the origin code, like some plugin feature?

Hello @GGBond8488 , Could you provide more information about what the preprocessing and postprocessing you want to do before running your `tritonserver` instance? Have you taken a look at the...

Segmentation fault

Hello @lizhenneng, Could you please provide the following information: 1. What environment is the `tritonserver --model-repository=` being run in? If it is in a published Triton container, what version? 2....

Segmentation fault

Closing due to inactivity. Please let us know if you would like to reopen the issue for follow-up.

Error: unpack_from requires a buffer of at least ... bytes for unpacking ... bytes at offset 4 (actual buffer size is ...)

Hello @adisabolic @suhaneshivam @ohad83 , Thank you @coder-2014 for diagnosing this issue. The following PR should resolve this issue: https://github.com/triton-inference-server/python_backend/pull/384. This fix will tentatively be a part of the 24.11...