chillingche

chillingche's Stars

• All-Hands-AI/OpenHands

  🙌 OpenHands: Code Less, Make More

  Language:Python43.2k3292k4.8k

• ShishirPatil/gorilla

  Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

  Language:Python11.7k972781k

• srush/GPU-Puzzles

  Solve puzzles. Learn CUDA.

  Language:Jupyter Notebook10.3k17032888

• OpenBMB/MiniCPM

  MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

  Language:Jupyter Notebook7.3k78224464

• EleutherAI/gpt-neox

  An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

  Language:Python7k1284511k

• HaujetZhao/CapsWriter-Offline

  CapsWriter 的离线版，一个好用的 PC 端的语音输入工具

  Language:Python3.1k18177256

• ARM-software/ComputeLibrary

  The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.

  Language:C++2.9k2301.1k785

• ModelTC/lightllm

  LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

  Language:Python2.8k22191220

• HazyResearch/ThunderKittens

  Tile primitives for speedy kernels

  Language:Cuda1.9k343494

• huggingface/nanotron

  Minimalistic large language model 3D-parallelism training

  Language:Python1.4k4393138

• facebookresearch/MobileLLM

  MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

  Language:Python1.2k231267

• mlfoundations/dclm

  DataComp for Language Models

  Language:HTML1.2k3768110

• kvcache-ai/ktransformers

  A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

  Language:Python831176747

• IST-DASLab/marlin

  FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

  Language:Python680163052

• RUC-GSAI/YuLan-Chat

  YuLan: An Open-Source Large Language Model

  Language:Python59451256

• allenai/OLMoE

  OLMoE: Open Mixture-of-Experts Language Models

  Language:Jupyter Notebook531101139

• Cornell-RelaxML/quip-sharp

  Language:Python514126844

• huggingface/cosmopedia

  Language:Python483121245

• pcg-mlp/KsanaLLM

  Language:C++302112730

• MegEngine/MegPeak

  Language:C++24891439

• bytedance/ABQ-LLM

  An acceleration library that supports arbitrary bit-width combinatorial quantization operations

  Language:C++24181926

• OpenGVLab/EfficientQAT

  EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

  Language:Python23742518

• quic/qidk

  Language:C11975227

• n-o-o-n/idp_hexagon

  Hexagon processor module for IDA Pro disassembler

  Language:C++104101622

• tlc-pack/libflash_attn

  Standalone Flash Attention v2 kernel without libtorch dependency

  Language:C++9915513

• Cornell-RelaxML/qtip

  Language:Python9811910

• HandH1998/QQQ

  QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.

  Language:Python935258

• LLM360/amber-data-prep

  Data preparation code for Amber 7B LLM

  Language:Python848210

• quic/efficient-transformers

  This library empowers users to seamlessly port pretrained models and checkpoints on the HuggingFace (HF) hub (developed using HF transformers library) into inference-ready formats that run efficiently on Qualcomm Cloud AI 100 accelerators.

  Language:Python579836

• ise-uiuc/xft

  XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts

  Language:Python29242