luliyucoordinate

luliyucoordinate's Stars

• NX-AI/flashrnn

  FlashRNN - Fast RNN Kernels with I/O Awareness

  Language:Python59

• microsoft/FractalTensor

  Language:Python133

• andrewkchan/yalm

  Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O

  Language:C++16712

• AIDC-AI/Marco-o1

  An Open Large Reasoning Model for Real-World Solutions

  Language:Python1.2k62

• howardlau1999/rdmapp

  C++ interfaces for RDMA access

  Language:C++624

• microsoft/TileFusion

  Language:C++315

• zhihu/ZhiLight

  A highly optimized LLM inference acceleration engine for Llama and its variants.

  Language:C++39330

• KONAKONA666/q8_kernels

  Language:Cuda403

• Tencent/HunyuanVideo

  HunyuanVideo: A Systematic Framework For Large Video Generation Model

  Language:Python6.5k486

• DefTruth/hgemm-tensorcores-mma

  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA PTX and CuTe API (Write for Fun 👀~)

  Language:Cuda37

• lllyasviel/IC-Light

  More relighting!

  Language:Python7.1k413

• NVIDIA/Star-Attention

  Efficient LLM Inference over Long Sequences

  Language:Python32314

• mlc-ai/xgrammar

  Efficient, Flexible and Portable Structured Generation

  Language:C++49924

• facebookexperimental/triton

  Github mirror of trition-lang/triton repo.

  Language:C++144

• CalebDu/Awesome-Cute

  Language:C++222

• cchan/tccl

  extensible collectives library in triton

  Language:Python754

• mirage-project/mirage

  Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA

  Language:C++68439

• mit-han-lab/nunchaku

  SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

  Language:Cuda53727

• chengzeyi/ParaAttention

  [WIP] Context parallel attention that works with torch.compile

  Language:Python625

• mlc-ai/tokenizers-cpp

  Universal cross-platform tokenizers binding to HF and sentencepiece

  Language:C++28665

• NVlabs/COAT

  Language:Python451

• feifeibear/ChituAttention

  Quantized Attention on GPU

  Language:Python33

• LeiWang1999/Stream-k.tvm

  Language:Python181

• bytedance/ShadowKV

  ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

  Language:Python1406

• NVIDIA/cccl

  CUDA Core Compute Libraries

  Language:C++1.3k170

• DD-DuDa/Cute-Learning

  Examples of CUDA implementations by Cutlass CuTe

  Language:Makefile12013

• KuangjuX/PyKernelCollection

  Collection of algorithms implemented using PyTorch and Triton.

  Language:Python5

• INT-FlashAttention2024/INT-FlashAttention

  Language:Python533

• yangjianxin1/Firefly

  Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

  Language:Python6k532

• ruikangliu/FlatQuant

  Official PyTorch implementation of FlatQuant: Flatness Matters for LLM Quantization

  Language:Python817