Deep Gandhi
Deep Gandhi
Hi @itsPreto, Its possible what we might have multiple ways to go about this including the ones Tony mentioned. Could you provide a more detailed explanation of the use case...
Hey @Emasoft, Just catching up on this. We now have support to load and interact with diffusion models within our platform. You can download one from Model Zoo or from...
Hi @Emasoft, Our vLLM and Sglang plugins also support multimodal models now allowing image inputs you can check those out as well! Just closing this issue now but please open...
We're tracking things here: #426 We have things working with Linux but have hit some roadblocks with WSL if anyone has experience on navigating those issues mentioned at the end...
Duplicate of #426
Adding an update here too that we were able to solve the WSL issues. We're waiting on getting things merged after proper testing and then we'll ship out support
Hello everyone! We now support AMD GPUs - install instructions [here](https://transformerlab.ai/docs/install/install-on-amd) :) Please provide some feedback and we'd be happy to keep improving on this!
Which trainer was this happening for? Does it still happen?
I tried to do this by installing aqlm, but it looks like there are some build issues of aqlm with cuda 12.8 and torch 2.8: ``` Error occurred in generation...
## Notes - Need to make vLLM work because the Ray error blocks AMD - Nanotron requires flash-attn and currently flash-attn build breaks for us, need to check because the...