chu-tianxiang

chu-tianxiang's Stars

• xai-org/grok-1

  Grok open release

  Language:Python49.5k5622098.3k

• hpcaitech/Open-Sora

  Open-Sora: Democratizing Efficient Video Production for All

  Language:Python22.1k1864902.2k

• LargeWorldModel/LWM

  Large World Model With 1M Context

  Language:Python7.1k6671551

• HVision-NKU/StoryDiffusion

  Accepted as [NeurIPS 2024] Spotlight Presentation Paper

  Language:Jupyter Notebook5.9k86143593

• pytorch-labs/gpt-fast

  Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

  Language:Python5.6k61104512

• meta-llama/llama-agentic-system

  Agentic components of the Llama Stack APIs

  Language:Python3.2k3835308

• DefTruth/Awesome-LLM-Inference

  📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

  2.7k906185

• pytorch/torchtitan

  A native PyTorch Library for large model training

  Language:Python2.5k39165192

• predibase/lorax

  Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

  Language:Python2.2k34242142

• baaivision/Emu

  Emu Series: Generative Multimodal Models from BAAI

  Language:Python1.6k218886

• BBuf/how-to-optim-algorithm-in-cuda

  how to optimize some algorithm in cuda.

  Language:Cuda1.5k249128

• noamgat/lm-format-enforcer

  Enforce the output format (JSON Schema, Regex etc) of a language model

  Language:Python1.5k1311267

• deepseek-ai/DeepSeek-LLM

  DeepSeek LLM: Let there be answers

  Language:Makefile1.4k243293

• flashinfer-ai/flashinfer

  FlashInfer: Kernel Library for LLM Serving

  Language:Cuda1.4k16114123

• NVIDIA/cccl

  CUDA Core Compute Libraries

  Language:C++1.2k301.4k156

• Vahe1994/AQLM

  Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf and PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression https://arxiv.org/abs/2405.14852

  Language:Python1.2k1985175

• google-research/deduplicate-text-datasets

  Language:Rust1.1k1341111

• kvcache-ai/Mooncake

  Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

  1.1k12423

• zhuzilin/ring-flash-attention

  Ring attention implementation with flash attention

  Language:Python570103445

• Cornell-RelaxML/quip-sharp

  Language:Python499126244

• mit-han-lab/qserve

  QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

  Language:Python42193020

• LLMServe/DistServe

  Disaggregated serving system for Large Language Models (LLMs).

  Language:Jupyter Notebook33344135

• Bruce-Lee-LY/cuda_hgemm

  Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction.

  Language:Cuda28341265

• KnowingNothing/MatmulTutorial

  A Easy-to-understand TensorOp Matmul Tutorial

  Language:C++28381130

• efeslab/Atom

  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving

  Language:Cuda274101924

• spcl/QuaRot

  Code for QuaRot, an end-to-end 4-bit inference of large language models.

  Language:Python270114220

• AlibabaResearch/flash-llm

  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity

  Language:Cuda1765715

• AILab-CVC/VL-GPT

  VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation

  841922

• chu-tianxiang/llama-cpp-torch

  llama.cpp to PyTorch Converter

  Language:Cuda26125

• Superjomn/cuda-from-scratch

  Language:Cuda2300