-
This requirement is HuggingFace Accelerate to support the Gaudi architecture, a high-performance AI accelerator developed by Habana Labs.
-
Starting point for a Gaudi Integration can be the JugTrack subproject of EIC`s juggler framework ( to be merged with key4hep)
https://github.com/eic/juggler/tree/master/JugTrack
-
Hi,
It is possible to access the PDG table from Geant4 with few lines of C++ code [[link](https://geant4-forum.web.cern.ch/t/example-showing-how-to-retrieve-particle-properties/12265)]. The motivat…
-
What I understand about this is actually deploy a model (e.g Llama3.1-70B-Instruct) by using 'vllm serve Llama3.1-70B-Instruct ... ' and then config the url and model name to llama-stack for LLM capab…
-
In principle this part
https://github.com/key4hep/key4hep-tutorials/blob/2a8ba424f71b5ba41e9c8a6b2a3a4c01f1b7a9d7/edm4hep_analysis/.solution/make_plots.py#L12-L13
of the edm4hep analysis can be simp…
-
### System Info
Linux gaudi2-wsf-test 5.15.0-92-generic #102-Ubuntu SMP Wed Jan 10 09:33:48 UTC 2024 x86_64 x86_64 x86_64 GNU/Linux
docker image: ghcr.io/huggingface/tgi-gaudi:2.0.0
###…
-
### System Info
```shell
Docker image: pytorch-installer-2.3.1:1.17.0-417
optimum-habana: main branch
```
### Information
- [ ] The official example scripts
- [X] My own modified script…
-
Hi,
it seems there is an example/test that is making the k4geo PR fail [1],
```
6/17 Test #9: geant_fullsim_fccee_lar_pgun.py ......***Failed 2.72 sec
Traceback (most recent call last):
…
-
Currently the TGI have [tgi-gaudi](https://github.com/huggingface/tgi-gaudi) to support the HPU for Gaudi 2 and also VLLM is included their [roadmap in Q1 2024](https://github.com/vllm-project/vllm/is…
-
I wanted to load Whisper Jax on Intel datacentre GPU Max series. I was wondering should I use Intel OpenXLA extension or Intel extension for transformers? not sure if openxla supports quantisation by …