-
I wanted to know, if there are any test cases available already for testing IPsec offloading feature? If not, is anyone working on it from the community ?
-
### System Info
pytorch==2.2.0
transformers==4.36.2
8 A100 80GB gpus
### Information
- [ ] The official example scripts
- [X] My own modified scripts
### 🐛 Describe the bug
When usin…
-
Is this something we should make the operator do by default for Enterprise Search?
_Originally posted by @thbkrkr in https://github.com/elastic/cloud-on-k8s/issues/7898#issuecomment-2…
pebrc updated
3 months ago
-
![Screenshot_2](https://github.com/user-attachments/assets/0dafa3ce-16fe-4cd4-8a12-ee2ba10b3fde)
```
Patching LoRA by precomputing model weights.
Patching LoRAs for KModel: 94%|█████████████…
-
The `accelerator` supports running in multiple GPUs and multiple CPUs scenarios.
Can I run `accelerate` in scenarios where both CPUs and GPUs exist at the same time?
For example, machine 1 uses th…
-
Hey everyone, awesome project :-) am having fun playing around with it, but I think my GPU isn't being utilised. I can see my CPU maxing out, and not seeing much of a change in my GPU usage, just wond…
-
GTK 4.14 gained support for graphics offloading, see https://blog.gtk.org/2023/11/15/introducing-graphics-offload/ It would be nice if clapper made use of that.
This probably requires porting the c…
-
https://kevin-zhang-sysu.github.io/2024/09/12/MOE-Offloading/?
这篇文章提出了如何在资源受限的消费级硬件上高效地运行稀疏专家混合(MoE)语言模型的方法。将Mixtral-8x7B这个需要100G以上算力才能部署的模型在12G显存+11G内存的组合下跑出来。论文:https://arxiv.org/abs/2312.17238Co…
-
Offloading compiled pipelines back and forth (or at least their weights) is a useful feat when dealing with multiple models on a single device with limited VRAM (but a lot of RAM). This doesn't seem p…
-
Is it currently possible to offload Wallpaper Engine to use the dedicated (NVIDIA) GPU over defaulting to integrated GPU, in regard to rendering scene wallpapers?
I've looked through older issue, w…