-
python -m llava.serve.controller --host 0.0.0.0 --port 10000
python -m llava.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000 --port 40000 --worker http://localhost:40000 --model…
-
### Bug description
When training a model with multiple GPUs (e.g. 2) and setting `num_workers` of Dataloader to be greater than zero, the Dataloader worker will say `CUDA error: initialization err…
-
### What happened + What you expected to happen
The bug:
We use ray start script to manually bootstrap our ray cluster: https://github.com/ray-project/ray/blob/master/python/ray/scripts/scripts.py…
-
### My current environment
- 8 * H800
- CUDA 11.8
- vllm 0.5.3post1
- python 3.9
I'm using vllm to deploy llama3 405B-instruct-FP8,But when deployed, it report an error:
```
INFO 07-24 22…
-
(myconda) root@q80JeX:~/Downloads/walk-these-ways-go2-main/scripts# python play.py
Importing module 'gym_38' (/root/Downloads/isaacgym/python/isaacgym/_bindings/linux-x86_64/gym_38.so)
Setting GYM_…
-
Not sure if this is already possible or what is needed here, but it would be useful to emit telemetry about how long it takes between the host sending a request to the worker and the worker starting w…
-
See: https://stackoverflow.com/questions/30323224/deploying-a-minimal-flask-app-in-docker-server-connection-issues/58138250#58138250
-
### Bug summary
Up until 3.0.0rc18 task run completions were registered correctly with a local Prefect server, but after that with 3.0.0rc19 and 3.0.0rc20 the list of task runs remain empty even afte…
-
### Bug description
Cache warm-up is not functioning when configured using the latest version (3.1.1rc1) and the previous one (3.1.0) in kubernetes enviroment (with Helm chart version 0.2.15 or ear…
-
### Investigative information
###### Please provide the following:
- Timestamp: 2023-06-28 08:58:35.849
- Function App name: https://raster.azurewebsites.net
- Function name(s) (as appropriate…