Maosheng Liao
Maosheng Liao
If there are still someone has a problem with `g2o_viewer` under 14.04, I wrote a [blog](https://blog.bobliao.fun/2019/04/30/g2o-in-ubuntu14-04/). You can have it a look.If you have any questions, contact with me. 我写了一篇关于g2o的组件在ubuntu14.04下如何安装的博客,需要的可以参考一下.
@winnietsang If you update this, you should document it.
@winnietsang And I didn't see this. https://github.com/onnx/onnx-tensorflow/blob/main/doc/API.md#onnx_tfbackend_reptensorflowrepexport_graph Now I want to know how can I export frozen graph? should I need to convert it to frozen graph use tensorflow API？Glad...
@hao0917 能微调到百分位，也算是辛苦了:laughing:
I got the same error. Seems the assertion failed in `integer_subbyte`, but that's weird.
Thanks for your feeding back. Much better now! Thanks!
Thanks for replying. Hope to see the fp8 support available.
> > Thanks for replying. Hope to see the fp8 support available. > > Hi @foreverlms, > > It is available now. Going to revise fp16 soon. Thanks, this could...
> @foreverlms may you paste the gsm8k result? (triton backend vs flashinfer backend) > > ```shell > python3 benchmark/gsm8k/bench_sglang.py --num-shots 8 --num-questions 1319 --parallel 1319 > ``` Is this for...
Got: ``` Accuracy: 0.453 Invalid: 0.005 Latency: 37.627 s Output throughput: 4522.078 token/s ``` Compared with mla not enabled: ``` Accuracy: 0.659 Invalid: 0.002 Latency: 40.824 s Output throughput: 4552.229...