Alternatives and similar repositories for LLM-Inference-Acceleration

Users that are interested in LLM-Inference-Acceleration are comparing it to the libraries listed below

• galeselee / Awesome_LLM_System-PaperList
  Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…
  ☆282Updated 8 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆119Updated last year
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆113Updated 4 months ago
• chenhongyu2048 / LLM-inference-optimization-paper
  Summary of some awesome work for optimizing LLM inference
  ☆139Updated this week
• MoE-Inf / awesome-moe-inference
  Curated collection of papers in MoE model inference
  ☆308Updated last month
• madsys-dev / deepseekv2-profile
  ☆152Updated 9 months ago
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆142Updated 10 months ago
• TreeAI-Lab / Awesome-KV-Cache-Management
  This repository serves as a comprehensive survey of LLM development, featuring numerous research papers along with their corresponding co…
  ☆255Updated 4 months ago
• HarryWu99 / llm_kvcache_sparsity
  Implement some method of LLM KV Cache Sparsity
  ☆42Updated last year
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆97Updated 11 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆132Updated last month
• CalebDu / Awesome-Cute
  ☆112Updated 6 months ago
• mdy666 / mdy_triton
  ☆150Updated 5 months ago
• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆82Updated this week
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆224Updated 2 years ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆190Updated last month
• AlibabaPAI / FLASHNN
  ☆102Updated last year
• LDLINGLINGLING / nano_vllm_note
  注释的nano_vllm仓库，并且完成了MiniCPM4的适配以及注册新模型的功能
  ☆108Updated 3 months ago
• microsoft / chunk-attention
  ☆82Updated 7 months ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆93Updated 5 months ago
• gty111 / gLLM
  gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling
  ☆51Updated this week
• thu-pacman / SmartMoE-AE
  ATC23 AE
  ☆47Updated 2 years ago
• kwai / Megatron-Kwai
  LLM training technologies developed by kwai
  ☆66Updated last week
• InternLM / Awesome-LLM-Training-System
  ☆44Updated last year
• Ascend / triton-ascend
  Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend
  ☆86Updated this week
• DicardoX / Research-Space
  This repository is established to store personal notes and annotated papers during daily research.
  ☆165Updated this week
• interestingLSY / swiftLLM
  A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …
  ☆292Updated 5 months ago
• sunkx109 / GPUs-Specs
  Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM
  ☆67Updated 3 months ago
• mit-han-lab / parallel-computing-tutorial
  ☆176Updated 2 years ago
• DD-DuDa / Cute-Learning
  Examples of CUDA implementations by Cutlass CuTe
  ☆254Updated 5 months ago