Zhoulong Jiang
Zhoulong Jiang
@PatriceVignola each package can have its own package name,the only requirement is the pluggable device library should be copied to `tensorflow-plugins` folder, I will update the tutoral example code. Thanks
@penpornk we have update the graph optimization C API part, including sample code. Thanks.
Hi, I use some pictures with these models, it seems that some work but some not work on cpu, but it can render correctly on Paintschainer website, does the model...
@adis98 I have the same issue with "AssertionError: [1, None]" when running lm.one_billion_wds.OneBWdsGPipeTransformerWPM, I saw you comment that it was the issue of input generator, does it mean it was...
thanks
@alexnick83 is there any experimental code that I can reproduce some fpga performance data shown in the paper? THanks
@alexnick83 thanks for the info, how ever, I tried to benchmark the test under polybench, it seems dace_cpu and dace_gpu is mush slower than numpy(8-10x slower), such as the following...
> I think the title should be 2.12 not 1.12, correct? I'll edit if that was a typo. > > We've seen this before, and its due to the profiler...
@ericdnielsen I install the profiler plugin and pip install the protobuf==3.20.1, the protoc issue is disappeared, however the profiler data can't show in tensorboard, I have host.xplane.pb in log dir,...
@sobomax thanks for the great info you provided. We get the similar picture when running Llama2 inference models using heaptrack, we also see the top1 memory identified by the tool...