-
### System Info
- docker image: nvcr.io/nvidia/tritonserver:24.05-trtllm-python-py3
- tensorrt_llm: 0.9.0
### Who can help?
@kaiyux @byshiue
### Information
- [ ] The official example scripts…
-
Where you have a custom index that contains rows for multiple models, it would be nice to be able to filter those lookups to include items of a specific type. For example:
```
index = MyCustomInde…
-
**Bug description**
When using any of the AWS / Bedrock models, the documentation states "The region property is compulsory." But this should not be the case since SpringAI uses the AWS SDK for Java…
-
### Your current environment
The output of `python collect_env.py`
```text
Collecting environment information...
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch…
-
Hello, Author. Your paper mentioned that the shared encoder is jointly trained in stage I, but the two models are separated in your code. I'm very confused. Can you help me solve it？3q
-
### Describe the issue
Until now we were creating our Ort::Session object by passing it the path of our model (.onnx file).
Now we are trying to create the Session object from the bytes already read…
-
01:54:47-255686 INFO Starting Text generation web UI
01:54:47-260684 WARNING trust_remote_code is enabled. This is dangerous.
01:54:47-268684 INFO Loading the extension "openai"
01:54:47-4…
-
### Checklist
- [X] The issue exists after disabling all extensions
- [X] The issue exists on a clean installation of webui
- [ ] The issue is caused by an extension, but I believe it is caused by a …
-
I think empty buffers should be valid. SYCL2020 3.10 says: "The minimum number of elements in a buffer object is zero."
```cpp
#include
#include
#include
// use namespace cl::sycl as sycl …
-
Upon starting the last cell to start SD, I receive the following error each time I have tried, including after disconnecting and re-running the cells:
`Downloading: "https://github.com/DagnyT/hardn…