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
  ☆67Updated last year
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆216Updated last year
• project-etalon / etalon
  LLM Serving Performance Evaluation Harness
  ☆79Updated 5 months ago
• WukLab / preble
  Stateful LLM Serving
  ☆79Updated 4 months ago
• EfficientMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆215Updated last month
• INT-FlashAttention2024 / INT-FlashAttention
  ☆80Updated 6 months ago
• efeslab / fiddler
  [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
  ☆225Updated 8 months ago
• flexflow / flexflow-serve
  FlexFlow Serve: Low-Latency, High-Performance LLM Serving
  ☆50Updated last week
• ScalingIntelligence / hydragen
  Hydragen: High-Throughput LLM Inference with Shared Prefixes
  ☆41Updated last year
• tonyzhang617 / nomad-dist
  ☆37Updated last year
• SymbioticLab / Oobleck
  A resilient distributed training framework
  ☆94Updated last year
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆44Updated this week
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆71Updated 3 months ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆64Updated last month
• triton-lang / kernels
  ☆85Updated 9 months ago
• ovg-project / kvcached
  kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.
  ☆35Updated last week
• microsoft / AttentionEngine
  ☆75Updated 2 months ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆155Updated last month
• efeslab / Atom
  [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  ☆318Updated last year
• microsoft / nnscaler
  nnScaler: Compiling DNN models for Parallel Training
  ☆114Updated this week
• tyler-griggs / melange-release
  ☆47Updated last year
• microsoft / chunk-attention
  ☆78Updated 3 months ago
• ByteDance-Seed / StragglerAnalysis
  ☆38Updated 3 months ago
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆123Updated 8 months ago
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆79Updated 2 weeks ago
• osayamenja / Kleos
  Complete GPU residency for ML.
  ☆37Updated last week
• YaoJiayi / CacheBlend
  ☆125Updated 3 weeks ago
• UChi-JCL / CacheGen
  ☆116Updated 9 months ago
• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆80Updated 11 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆93Updated last month