-
### 🚀 The feature, motivation and pitch
Rerank models are essential to RAG workflow. There are quite a few models available, such as jina-reranker-v2. Some inference frameworks already support rera…
-
Also where can I specify project name or project source path for which I want to run inference script ? I ran the below command and it failed.
```
./scripts/inference --logLevel FINE --mode TYPEC…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### Reproduction
Hi There, I am observing a difference in output between llama factory inference and llama.cpp.
I am…
-
## What happened + What you expected to happen
When using the new `enable_env_runner_and_connector_v2` feature in RLlib, the `env_runners` do not have access to the GPU for inference on the env_runne…
-
I was attempting to try this out using the provided example, first cloning the repo and installing packages. I needed to manually add the tflite_runtime on my system.
`pip install tflite_runtime`
…
-
### Issue Type
Others
### OS
Mac OS
### OS architecture
x86_64
### Programming Language
Python
### Framework
PyTorch, ONNX
### Model name and Weights/Checkpoints URL
https://github.com/akan…
-
Giving good error messages when type inference fails is notoriously tricky. In [A Practical Framework for Type Inference Error Explanation](https://calvin.loncaric.us/research/mycroft-tr.pdf), Loncar…
-
Hello! I am replicating the ASR code from a paper in the espnet framework, where I replaced the self-attention module in the decoder with mamba. The modifications are as shown in the figure, and the r…
-
### System Info
NVIDIA GeForce 4090 Gpu
### Who can help?
_No response_
### Information
- [ ] The official example scripts
- [ ] My own modified scripts
### Tasks
- [ ] An officially supported …
-
### OpenVINO Version
2024.4.0
### Operating System
Other (Please specify in description)
### Device used for inference
NPU
### Framework
None
### Model used
YOLOv8s, YOLOv9c
### Issue descri…