ironartisan / awesome-compression1

Related projects ⓘ

Alternatives and complementary repositories for awesome-compression1

• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for multi head attention (MHA) using CUDA core for the decoding stage of LLM inference.
  ☆23Updated last week
• FreedomIntelligence / FastLLM
  Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];
  ☆34Updated 10 months ago
• TRT2022 / ControlNet_TensorRT
  天池 NVIDIA TensorRT Hackathon 2023 —— 生成式AI模型优化赛 初赛第三名方案
  ☆47Updated last year
• DataXujing / TensorRT-LLM-ChatGLM3
  大模型部署实战：TensorRT-LLM, Triton Inference Server, vLLM
  ☆26Updated 8 months ago
• GuoYiFantastic / IMelodist
  Music large model based on InternLM2-chat.
  ☆21Updated 3 months ago
• Oldpan / DeployIsAllYouNeed
  ☆117Updated last year
• Rayrtfr / FasterTransformer
  Transformer related optimization, including BERT, GPT
  ☆17Updated last year
• FeiGeChuanShu / trt2023
  NVIDIA TensorRT Hackathon 2023复赛选题：通义千问Qwen-7B用TensorRT-LLM模型搭建及优化
  ☆40Updated last year
• TRT2022 / trtllm-llama
  ☢️ TensorRT 2023复赛——基于TensorRT-LLM的Llama模型推断加速优化
  ☆44Updated last year
• shiyemin / light-hf-proxy
  A light proxy solution for HuggingFace hub.
  ☆44Updated last year
• sophgo / ChatGLM2-TPU
  run ChatGLM2-6B in BM1684X
  ☆48Updated 8 months ago
• SmartFlowAI / LLM101n-CN
  LLM101n: Let's build a Storyteller 中文版
  ☆116Updated 2 months ago
• shuyhere / all-about-llm
  大语言模型训练和服务调研
  ☆34Updated last year
• ArtificialZeng / llama3_explained
  the newest version of llama3，source code explained line by line using Chinese
  ☆22Updated 6 months ago
• ArtificialZeng / baichuan-speedup
  纯c++的全平台llm加速库，支持python调用，支持baichuan, glm, llama, moss基座，手机端流畅运行chatglm-6B级模型单卡可达10000+token / s，
  ☆45Updated last year
• chaoswork / llm_illustrated
  看图学大模型
  ☆175Updated 3 months ago
• liguodongiot / unify-easy-llm
  unify-easy-llm（ULM）旨在打造一个简易的一键式大模型训练工具，支持Nvidia GPU、Ascend NPU等不同硬件以及常用的大模型。
  ☆36Updated 3 months ago
• DataXujing / Bert_TensorRT
  Bert TensorRT模型加速部署
  ☆9Updated 2 years ago
• jiahe7ay / infini-mini-transformer
  This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…
  ☆52Updated 6 months ago
• andongBlue / SoLargeLM
  ☆22Updated last year
• SmartFlowAI / Hand-on-RAG
  顾名思义：手搓的RAG
  ☆110Updated 8 months ago
• zms1999 / SmartMoE
  A MoE impl for PyTorch, [ATC'23] SmartMoE
  ☆57Updated last year
• MonolithFoundation / Bumblebee
  A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.
  ☆36Updated 2 months ago
• SUSTech-IDEA / SUS-Chat
  SUS-Chat: Instruction tuning done right
  ☆47Updated 9 months ago
• luchangli03 / onnxsim_large_model
  simplify >2GB large onnx model
  ☆43Updated 8 months ago
• openmlsys / openmlsys-cuda
  Tutorials for writing high-performance GPU operators in AI frameworks.
  ☆122Updated last year
• yann168 / boshi-sample-solution
  ☆13Updated 11 months ago
• SkyworkAI / vllm
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆15Updated 5 months ago
• CyberCommy / baidu-qa-100w
  百度QA100万数据集
  ☆49Updated 11 months ago
• zhaochenyang20 / Prompt2Model-Self-Guide
  SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper
  ☆26Updated 5 months ago