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…
  ☆259Updated 4 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆108Updated last year
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆98Updated last week
• MoE-Inf / awesome-moe-inference
  Curated collection of papers in MoE model inference
  ☆210Updated 5 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…
  ☆164Updated 3 weeks ago
• chenhongyu2048 / LLM-inference-optimization-paper
  Summary of some awesome work for optimizing LLM inference
  ☆84Updated last month
• madsys-dev / deepseekv2-profile
  ☆145Updated 4 months ago
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆126Updated 6 months ago
• HarryWu99 / llm_kvcache_sparsity
  Implement some method of LLM KV Cache Sparsity
  ☆34Updated last year
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆216Updated last year
• interestingLSY / swiftLLM
  A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …
  ☆234Updated last month
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆59Updated last month
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆88Updated 7 months ago
• microsoft / chunk-attention
  ☆77Updated 3 months ago
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆93Updated 3 months ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆148Updated last month
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆58Updated 11 months ago
• AlibabaPAI / FLASHNN
  ☆96Updated 10 months ago
• zcli-charlie / Awesome-KV-Cache
  ☆71Updated 9 months ago
• CalebDu / Awesome-Cute
  ☆87Updated 2 months ago
• DD-DuDa / BitDecoding
  A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆52Updated last week
• InternLM / Awesome-LLM-Training-System
  ☆40Updated 11 months ago
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆87Updated 2 months ago
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆102Updated 2 months ago
• shenh10 / DeepSeek_Simulator
  ☆80Updated 3 months ago
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆168Updated 9 months ago
• lambda7xx / awesome-AI-system
  paper and its code for AI System
  ☆316Updated 3 months ago
• Gaffey / ExCP
  Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".
  ☆48Updated last year
• yinuotxie / Efficient-LLM-Inferencing-on-GPUs
  Penn CIS 5650 (GPU Programming and Architecture) Final Project
  ☆35Updated last year
• Bruce-Lee-LY / decoding_attention
  Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.
  ☆39Updated last month