BentoML

BentoML copied to clipboard

### Describe the bug the doc claims that --model-id can either be a model id or a path to the local model, however bento will always check that the provided...

Epsilon314

### Describe the bug Calling a zero-argument runner method (using either `method.run()` or `method.async_run()`) results in an error like the following: ```python 2023-12-21T11:19:12-0500 [ERROR] [runner:custom_runner:9] Traceback (most recent call last):...

connorbrinton

bug: bentoml.transformers.save_model() is constrained on image-classification?

1

### Describe the bug ```import torch from transformers import pipeline import bentoml pipe = pipeline( "automatic-speech-recognition", ) bentoml.transformers.save_model( "automatic-speech-recognition-whiser-large-v2", pipe, signatures={ "__call__": {"batchable": False} # Enable dynamic batching for model...

xinghua-qu

### Describe the bug When making a bento API request with a large payload (e.g. a JSON key-value dict with ~200 elements), I get the following error: ``` aiohttp.client_exceptions.ClientResponseError: 400,...

mqk

### Describe the bug gensim word2vec model ```python import os import mlflow from gensim.models.word2vec import Word2Vec class ScappyWrapper(mlflow.pyfunc.PythonModel): def load_context(self, context): file_path = os.path.join(context.artifacts["model_path"], "scappy_base.bin") self.model = Word2Vec.load(file_path) def predict(self,...

BangDaeng

feature: not able to install packages from private PyPI easily

3

### Feature request It would be great to propose an easy way to mount config files like .netrc before installing deps from a requirements.txt file ### Motivation I am not...

michaelromagne

[minor issue] The BentoML image becomes too heavy after including the dependency on nvidia-ml-py3.

2

https://github.com/bentoml/BentoML/blob/cc765bba83501f446297de31fdc819cd7dcc2901/pyproject.toml#L40C23-L40C23 To be precise, build times have increased since the `pynvml

KimSoungRyoul

bug: BentoML installation throwing mutable default <class 'bentoml.types.HTTPHeaders'> for field headers is not allowed: use default_factory

2

### Describe the bug We installed BentoML 0.13.1 as we cannot migrate to 1.x at this moment, the installation is throwing the following error when we are trying to run...

amustafi1986

bug: Http Server is not worked with Pytorch-Lightning without 'del sys.modules["prometheus_client"]'

18

### Describe the bug benotml serve {my_service}.py:svc --port 3001 is loaded and stdout shows log ```bash Prometheus metrics for HTTP BentoServer from "{my_service}.py:svc" can be accessed at http://localhost:3001/metrics 2023-04-25T10:49:47+0900 [INFO]...

bobby-ohouse

### Describe the bug I am not able to import a secret as documented in "Advanced Containerization" : https://docs.bentoml.org/en/latest/guides/containerization.html#mount-credentials-from-host ### To reproduce ``` ~/gg-workspace/ml-detector/bento_config (mromagne/MLE-91/load-test-ec2*) » cat ../bentofile.yaml service: "services.py:svc"...

michaelromagne