-
### Bug Description
I try to assign:
from llama_index.core import Settings
Settings.embed_model = "local:BAAI/bge-m3"
After assigning embed_model it starts download process from huggingface. T…
aabor updated
4 months ago
-
Hi, I tried to install intel-i915-dkms with command
```
sudo apt install -y intel-i915-dkms
```
on Ubuntu 22.04 with Kernel 6.8.0-45-generic and dpkg returns error:
```
Reading package li…
-
Hi ,I have attempted to use the framework to generate a premise however I cannot even start the servers.
I have attempted the following steps:
- Clone the repo to a clean environment (ucloud VM)…
-
I'm going through the standard "new contributor tries to make himself useful" steps and (predictably) picked out the documentation as an area in which I can make progress toward that goal. There are …
-
Description:
When I am executing the news_pull task, there are no problems with other steps in the save operation. An error occurs when executing the summarize method. How can I solve this problem?
…
-
### Your current environment
```text
Collecting environment information...
WARNING 06-13 12:05:09 _custom_ops.py:14] Failed to import from vllm._C with ModuleNotFoundError("No module named 'vllm._C…
-
### Your current environment
```text
root@9206753dc19c:/# python3 collect_env.py
Collecting environment information...
PyTorch version: 2.2.1+cu121
Is debug build: False
CUDA used to build PyTor…
-
I am using a 13.2 ML Runtime Cluster w/ 28GB of RAM via databricks. Have no problem installing vllm, but import statement is showing the following error. Have pytorch installed as well.
ImportErr…
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
No
### Source
source
### TensorFlow version
2.8.4
### Custom code
Yes
### OS platform and dist…
-
Hello all,
I have recently benchmarked completion token time, which is 30ms on an H100. However, with llama.cpp it is 10ms. Because [mistral.rs](https://github.com/EricLBuehler/mistral.rs) is built…