Peirong Zheng

- 感谢大神的好工具，已经超级强大了，帮我解决了大问题！ 1. 希望在查词时，默认英英词典，看不懂再选择英汉词典。不过我也可以手动切换哈哈。 2. 我调整了【夜间模式】：在这个界面，换上这两行代码就好啦。 color: #fff; background-color: black; 

Please correct this in the [README.md]

[Feature Suggest] Tensor Parallellism for Accelerating LLM

22

Dear Author, Your contribution is critical for the open-source community. The distributed-llama repo has implemented tensor parallelism from scratch. And the result is amazingly significant. However, there are still improvements...

可以添加更多人物及语音，特别是中文声优。

2

1. colab有[开源的派蒙VITS模型](https://colab.research.google.com/drive/1HDV84t3N-yUEBXN8dDIDSv6CzEJykCLw#scrollTo=oiPvCIJ_MHot) 2. huggingface还有几十个中日英三语的[语音合成模型](https://huggingface.co/spaces/Plachta/VITS-Umamusume-voice-synthesizer) 希望楼主早日添加更新！

network utilization

3

# Let's calculate the transfer time theoretically. ## llama3 8B The original experiment data is [here](https://github.com/b4rtaz/distributed-llama/discussions/41#discussioncomment-9435671). Since the transfer is full-duplex, there's no interference between uplink and downlink. So, we...

Dear author, I am using Raspberrry Pi 4B, and here is my result: 1. sgemm.py ```sh pi@node01:~/py-videocore6 $ PYTHONPATH=sandbox/ python3 examples/sgemm.py ==== sgemm example (1024x1024 times 1024x1024) ==== numpy: 0.08994...