-
Currently you can only run one exo instance on each device.
There are some design decisions here:
- Should we support running multiple exo instances on the same device, with one per GPU
- Or shou…
-
Co-authored with @SolitaryThinker @Yard1 @rkooo567
We are landing multi-step scheduling (#7000) to amortize scheduling overhead for better ITL and throughput. Since the first version of multi-step…
-
I'm following the tutorial [here](https://www.tensorflow.org/recommenders/examples/multitask) and I am wondering how to get a prediction for a given user.
Once training is done, how can I pass a user…
-
Hi, thanks for your excellent work!
I have modified the code like this:
```
device_ids = [0, 1, 2, 3, 4, 5, 6, 7]
self.model = torch.nn.DataParallel(self.model, device_ids=device_ids)
self.mo…
-
First, thanks for all your work on this repo, it's great stuff!
After fine-tune, how to correctly save the text encoder for use with:
CLIPTextModel.from_pretrained & StableDiffusionXLPipeline.from…
-
Hi, I'm trying to run finetune.py by 6 GPUs:
WORLD_SIZE=6 CUDA_VISIBLE_DEVICES=0,1,2,3,4,5 torchrun --nproc_per_node=6 --master_port=1234 finetune.py \
--base_model='./llama-7b-hf' \
--num_epo…
-
### Discussed in https://github.com/redis/go-redis/discussions/2764
Originally posted by **shamhub** October 18, 2023
Go supports client library to talk to Redis memory as cache. https://githu…
-
Good morning. I was doing a multi domain analysis and I was trying to understand how to analyze the PCA depending on parameters using studio.
I am not sure to completely understand the "alignment r…
-
**Is your feature request related to a problem? Please describe.**
I want to be able to use the whisper-1 model provided by OpenAI to transcribe text from audio. LLMs are also getting more multi-moda…
-
/kind feature
**Describe the solution you'd like**
Running inference on large NLP models requires spinning up a number of GPU hosts for [model parallelism](https://huggingface.co/docs/transformers…
hutm updated
3 months ago