Alternatives and similar repositories for LLM-Inference-Bench

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

• hao-ai-lab / MuxServe
  ☆62Updated 11 months ago
• project-etalon / etalon
  LLM Serving Performance Evaluation Harness
  ☆78Updated 3 months ago
• WukLab / preble
  Stateful LLM Serving
  ☆70Updated 2 months ago
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆211Updated last year
• MDK8888 / vllmini
  A minimal implementation of vllm.
  ☆41Updated 10 months ago
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆39Updated last month
• EfficientMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆195Updated 2 weeks ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆132Updated last month
• microsoft / nnscaler
  nnScaler: Compiling DNN models for Parallel Training
  ☆114Updated this week
• microsoft / chunk-attention
  ☆76Updated last month
• thu-pacman / FasterMoE
  ☆84Updated 3 years ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆73Updated 4 months ago
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆86Updated 2 years ago
• SymbioticLab / Oobleck
  A resilient distributed training framework
  ☆95Updated last year
• efeslab / fiddler
  [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
  ☆211Updated 6 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆88Updated last week
• abhibambhaniya / GenZ-LLM-Analyzer
  LLM Inference analyzer for different hardware platforms
  ☆69Updated last week
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆116Updated 6 months ago
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆158Updated 8 months ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆50Updated 2 weeks ago
• DD-DuDa / BitDecoding
  A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆36Updated last month
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆76Updated 9 months ago
• ByteDance-Seed / StragglerAnalysis
  ☆21Updated last month
• wangsiping97 / FastGEMV
  High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.
  ☆109Updated 10 months ago
• flexflow / flexflow-serve
  FlexFlow Serve: Low-Latency, High-Performance LLM Serving
  ☆41Updated 3 weeks ago
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆163Updated 10 months ago
• vllm-project / flash-attention
  Fast and memory-efficient exact attention
  ☆72Updated last month
• NEO-MLSys25 / NEO
  NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading
  ☆35Updated 3 months ago
• LMCache / lmcache-vllm
  The driver for LMCache core to run in vLLM
  ☆41Updated 4 months ago
• Azure / msccl
  Microsoft Collective Communication Library
  ☆65Updated 6 months ago