Nat Kershaw (MSFT)
Nat Kershaw (MSFT)
Hi @qihui-liu, You can load the local model using the LoadModelAsync API e.g. ``` ModelInfo loaded = await manager.LoadModelAsync("aliasOrModelId"); ```
Hi again @qihui-liu, we have identified a bug in model loading. Please stay tuned for a fix. In the mean time, you should be able to run the cached model...
Duplicate of #233
Hi @jmopuri-Intel, are you able to run the CLI to try to start the service manually? and then share logs so thay we can see what is happening. Also would...
@MaanavD How much clean up would we expect WinGet to do here? @snnn If the answer to the above is minimal, can the installer be modified to remove the cache...
The model can now be loaded directly from the cache but there is a stack trace and timeout beforehand ``` [11:47:15 ERR] Exception fetching models from Azure Foundry catalog $System.Net.Http.HttpRequestException:...
This issue still exists in 0.7.117 Repro steps. - Install foundry local - Run a model (successful) - Disconnect the network - Run the same model
Hi @ElSrJuez, it looks like the retry occurred after 10mins, which is the default TTL send to the model server. The load operation should not take 10 minutes. Is this...
@HaoHoo did you try the latest version on Mac? Instructions here: https://review.learn.microsoft.com/en-us/azure/ai-foundry/foundry-local/get-started?branch=main#option-1-quick-cli-setup
Thank you for reporting this. Can you please share the output of `foundry model list` with the version of Foundry Local that is not working. Also, are you running on...