Skip to content
View tpoisonooo's full-sized avatar
:electron:
wholeheartedly
:electron:
wholeheartedly
311 followers · 64 following
  • pjlab.org.cn
  • Shanghai

Achievements

Achievement: Starstruckx3Achievement: Pair Extraordinairex3Achievement: QuickdrawAchievement: YOLOAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor
BetaSend feedback

Achievements

Achievement: Starstruckx3Achievement: Pair Extraordinairex3Achievement: QuickdrawAchievement: YOLOAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor
BetaSend feedback
Block or Report

Block or report tpoisonooo

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
tpoisonooo/README.md

Hi there 👋

My report:

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance arxiv2401.08772

My favorate projects:

  • llama onnx format and single demo without torch

  • how to optimize GEMM，armv7/aarch64/aarch64-int8/cuda/cuda-int4/vulkan all supported

  • ML solution for long-tailed demands, MegFlow is implemented with Rust and Python

Pinned

  1. YHs_Sample YHs_Sample Public

    Forked from Yinghan-Li/YHs_Sample

    Yinghan's Code Sample

    Cuda

  2. chgemm chgemm Public

    symmetric int8 gemm

    Assembly 65 12

  3. rust-ncnn rust-ncnn Public

    ncnn Rust API.

    Rust 33 7

  4. llama.onnx llama.onnx Public

    LLaMa/RWKV onnx models, quantization and testcase

    Python 324 28

  5. InternLM/HuixiangDou InternLM/HuixiangDou Public

    HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

    Python 825 72