-
In our new framework, users select performance, cost, and other models at the config level. How decoupled should these models be from each other? Sould we support using heterogeneous performance and c…
-
Refs #618
Refs #619
Refs #588
Refs #582
Refs #557
Refs #548
Refs #482
Refs #442
Refs #379
Refs #378
Refs #360
Refs #276
Refs #641
-
### Search before asking
- [X] I had searched in the [issues](https://github.com/eosphoros-ai/DB-GPT/issues?q=is%3Aissue) and found no similar issues.
### Operating system information
Linux
### P…
-
May subsume #107 #108
This should be an inclusive conversation, @pbuttigieg has specific use cases, include biocurators etc
cc @wdduncan
-
### Describe the bug
Current approach hard-coded with accessing bedrock-runtime client to use session with access_credentials. We need to handle a case where it can pick client with attached IAM role…
-
**Describe the bug**
When deploying the model, I received this error message (see screenshot below).
**To Reproduce**
Follow the instructions, deploy the model.
**Expected behavior**
The mode…
-
## Bug Description
TensorRT engine produces error when ran on Jetson for [fcn_resnet](https://pytorch.org/hub/pytorch_vision_fcn_resnet101/) model. However, it does not produce error when ran on d…
-
### System Info / 系統信息
SERVER:Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
PRETTY_NAME:"Debian GNU/Linux 11 (bullseye)"
python:3.11.5
conda:23.10.0
torch:2.4.1+cpu
### Running Xinference with D…
-
### Feature Type
- [ ] Adding new functionality to valor
- [ ] Changing existing functionality in valor
- [ ] Removing existing functionality in valor
### Problem Description
We should have supp…
-
Right now, the only place a user can see which model is active is in `barman diagnose`. We should have this information handy in the status and show-server output.