-
hello, can i once deploy several models for server ?
whcjb updated
3 weeks ago
-
Hi,
I am not logging any issue here but have a query [vague though]. I am deploying a model/adapter which is trained using unsloth. Is there a way out of missing out on the GPU requirement? or in oth…
-
-
While initial support was added for Azure OpenAI, there are outstanding issues with the current implementation.
**Currently only one deployment/model is supported.**
* If I want to use gpt-4o via …
-
**What would you like to be added**:
`model.Deployment.version` is deprecated and should be removed.
ref: https://github.com/pipe-cd/pipecd/blob/master/pkg/model/deployment.proto#L86-L87
**…
-
Add additional deployment models to the spec, such as aggregators, to address scalability.
-
Users can easily go through the project if deployed instead of forking the project and then checking the live version . In other words, make it live . Pls assign this task to me and
and assign me th…
-
AS a user
I WANT see a dropdown list that contains the list of deployment models
SO THAT I can select a deployment model to use
-
### System Info / 系統信息
# ComfyUI Error Report
## Error Details
- **Node Type:** DownloadAndLoadCogVideoModel
- **Exception Type:** AssertionError
- **Exception Message:** diffusers version 0.30…
-
/kind bug
**What steps did you take and what happened:**
When trying to deploy a large model (e.g. `granite-20b-code-instruct`) the `Pod` terminates before completion.
I use a `ServingRuntime` …