-
https://arxiv.org/pdf/2410.16663
On **Ascend NPUs**, our FastAttention can achieve a 10.7× speedup compared to the
standard attention implementation.
End-to-end performance evaluation of FastAtte…
-
### Search before asking
- [X] I have searched the Ultralytics [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar feature requests.
### Description
I have seen that r…
-
Hi,
When I use docker to deploy gpustack on Ascend platform, gpustack cannot read NPU information.
gpusta…
-
### Describe the issue
I see with this change compilation flag is persistent.
https://github.com/microsoft/onnxruntime/pull/22027/files
Is it possible to make it optional?
### Urgency
_No respon…
-
Hello, I am curious if there is an update on the timeline for supporting NPUs?
Thanks.
-
Hi! There is NPU in Intel processors.
https://www.intel.com/content/www/us/en/support/articles/000097597/processors.html
Are you planning to support something like this?
As I now Intel has t…
-
https://github.com/openvinotoolkit/openvino_notebooks/blob/latest/notebooks/hello-world/hello-world.ipynb
I try to compile this model (mobelinet-v3-tf/FP32) using Intel LNL NPU, so i changed code.
…
-
### **Environment :**
Intel Core Ultra 7 165H (Meteor Lake),
Ubuntu 24.04 (LTS),
Kernel : 6.8.0-49-generic,
Python 3.12,
OpenVINO 2024.5.0,
GPU Driver : 24.31.30508.7,
NPU Driver : 1.5.1 [Afte…
-
Could someone help me with optimizing models for NPU ? I want to optimize Florence2 for NPU and also want to study if there can be a generic method to optimize a model to run on NPUs.
-
这个 project 默认都是支持英伟达 GPU，国内在硬件生态上正在发生大的变化。请问，是否有支持昇腾 NPU 的计划？