Guoliang Shi comments

Results 6 comments of


                                            Guoliang Shi

How to solve this problem about compile?

I also meet this error, i think different version result this problem. so i create a new environment with tensorflow 1.9, CUDA 9.0 and it works.

[NPUW] Fix Omni Thinker LLM with Two Outputs Issue

@AsyaPronina @dmatveev Please take a look.

[NPUW] Fix Omni Thinker LLM with Two Outputs Issue

@AsyaPronina @AlexanderKalistratov not sure if you have other comments about this PR

[NPUW] Add Eagle3 (top-1) pipeline support with new I/O

> Hello Dear @GuoliangShiIntel ! Thanks a lot for such a great contribution!! > > I left my comments below. One of my main concerns is fail-safe execution of `Eagle3Extension`....

[NPUW] Add Eagle3 (top-1) pipeline support with new I/O

@AsyaPronina @AlexanderKalistratov Today, I aligned with the GPU pipeline and identified some model structure changes aimed at improving performance. Consequently, we will implement similar changes for the NPU pipeline, as...

[NPUW] Add Eagle3 (top-1) pipeline support with new I/O

Hi @AsyaPronina @AlexanderKalistratov I've addressed all review comments. What's the next step? Do we need additional reviews, or should we wait for the GenAI Pipeline PR to be ready before...