Greg

Implement Vision Grid Transformer for Document Layout Analysis

2

Implement [Vision Grid Transformer for Document Layout Analysis](https://arxiv.org/abs/2308.14978) AlibabaResearch recently published a new model for Document Layout Analysis which sets a new benchmark in the task of Document Layout Analysis....

**Describe the feature** Add support for CUDA-MPS to take advantage of new optimizations. Requesting: - [ ] Setup scripts (Installation / Ansible / Docker ) - [ ] Refactor exiting...

certificate verify failed: unable to get local issuer certificate

1

**Describe the bug** During startup we are getting following exception. ``` INFO marie@33 Kwargs : {'metas': {'name': '', 'description': '', 'workspace': '', 'py_modules': ['marie.executor.text']}, 'requests': {}, 'dynamic_batching': {}, 'runtime_args': {'workspace':...

No working C++ compiler found in torch._inductor.config.cpp.cxx: (None, 'g++')

3

**Describe the bug** While running marie container `3.0.22-cpu' we get in the logs. ``` [2023-11-29 22:29:33,093] torch._dynamo.convert_frame: [WARNING] due to: [2023-11-29 22:29:33,093] torch._dynamo.convert_frame: [WARNING] Traceback (most recent call last): [2023-11-29...

gRPC error: StatusCode.UNAVAILABLE keepalive watchdog timeout

1

After service runs for extended amount of time we start receiving following error ``` ERROR 065301be-28ca-7efa-8000-9b486b83e4ea : AsyncGRPCClient@1192118 gRPC error: StatusCode.UNAVAILABLE keepalive watchdog timeout [10/18/23 12:55:14] None The ongoing request...

**Describe the bug** Getting an segfault while running `marie server`. This is problematic as it creates a `defunct` aka `zombie` process cause the kernel to leave a task stuck in...

**Describe the bug** While migrating to `torch-2.2.0.dev20231126+cu118` run into the issue. This could be due to the nature that this is a `dev` release but adding it for tracking purposes....

**Describe the bug** When running `ClassificationPipeline` we get the following warning. ``` You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a...

While running consul health check we see health check failures due to following : ```sh Get "http://127.0.0.1:51000/dry_run": context deadline exceeded (Client.Timeout exceeded while awaiting headers) ```

Negative region coordinates cause broadcast error. ``` ERROR 06538401-2115-7838-8000-234c29f83b38 : VotingOcrEngine@1809103 Extract error Traceback (most recent call last): File "/home/gbugaj/dev/marieai/marie-ai/marie/ocr/ocr_engine.py", line 128, in process_single results = self.__process_extract_regions( File "/home/gbugaj/dev/marieai/marie-ai/marie/ocr/ocr_engine.py", line...