-
### Enhancement Description
Each model integration is composed of two aspects: an `*Api` class calling the model provider over HTTP, and a `*Client` class encapsulating the LLM specific aspects.
…
-
Hello,
While running demo/multi-model-exec/npu_modelsx4_demo, I was found the following error.
>Running ...
Close window to stop
gui is starvatting!!
gui is starvatting!!
gui is starvattin…
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
source
### TensorFlow version
2.13
### Custom code
Yes
### OS platform and dist…
-
I've been trying to quantize and run the Meta-Llama-3.1-8B-Instruct-2.3bit model with group number set to 4, and successfully run the model when k1(centroids) is 4096 as in the paper. However, anythin…
-
### Do you need to file an issue?
- [x] I have searched the existing issues and this feature is not already filed.
- [ ] My model is hosted on OpenAI or Azure. If not, please look at the "model provi…
-
Does the evaluation support multi GPU? I used the script to evaluate bge-m3 on one task, and it takes more than 10 hours on one GPU. p.s. I tried to enlarge the batch_size, but always leads to OOM.
`…
-
**Bug** 💥
I am Trying to train the model on doclaynet dataset using multiple gpu, but facing error as CUDA error: device-side assert triggered
CUDA kernel errors might be asynchronously reported at …
-
Multi-scale relief model and Sky illumination visualizations don't work as they should. Our main goal for RVT plugin is to output the correct results. We temporarily removed these two visualizations f…
-
Is it possible to use image references in 3D to 3D?
-
### Question
I'm working on a multi-tenant application using Prisma with PostgreSQL, where each tenant has its own schema. I'm facing issues with Prisma recognizing the `vector` extension, which is…
emuye updated
1 month ago