Alternatives and similar repositories for LLM-Inference-Bench

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

• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆230Updated 2 years ago
• microsoft / tokenweave
  Efficient Compute-Communication Overlap for Distributed LLM Inference
  ☆66Updated last month
• efeslab / fiddler
  [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
  ☆249Updated last year
• hao-ai-lab / MuxServe
  ☆79Updated 2 months ago
• project-etalon / etalon
  LLM Serving Performance Evaluation Harness
  ☆82Updated 9 months ago
• vllm-project / flash-attention
  Fast and memory-efficient exact attention
  ☆105Updated this week
• tyler-griggs / melange-release
  ☆48Updated last year
• WukLab / preble
  Stateful LLM Serving
  ☆90Updated 9 months ago
• IBM / triton-dejavu
  Framework to reduce autotune overhead to zero for well known deployments.
  ☆90Updated 3 months ago
• meta-pytorch / KernelAgent
  Autonomous GPU Kernel Generation via Deep Agents
  ☆187Updated this week
• microsoft / chunk-attention
  ☆83Updated 8 months ago
• DeepLink-org / DLSlime
  DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
  ☆84Updated this week
• yinuotxie / Efficient-LLM-Inferencing-on-GPUs
  Penn CIS 5650 (GPU Programming and Architecture) Final Project
  ☆44Updated 2 years ago
• deepspeedai / DeepSpeed-Kernels
  ☆71Updated 8 months ago
• EfficientMoE / MoE-Infinity
  PyTorch library for cost-effective, fast and easy serving of MoE models.
  ☆265Updated 2 months ago
• flexflow / flexflow-serve
  FlexFlow Serve: Low-Latency, High-Performance LLM Serving
  ☆64Updated 3 months ago
• thu-pacman / FasterMoE
  ☆88Updated 3 years ago
• tonyzhang617 / nomad-dist
  ☆39Updated last year
• abcdabcd987 / libfabric-efa-demo
  ☆73Updated 11 months ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆94Updated 6 months ago
• Infrawaves / DeepEP_ibrc_dual-ports_multiQP
  Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport
  ☆70Updated 7 months ago
• microsoft / TileFusion
  TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.
  ☆105Updated 5 months ago
• INT-FlashAttention2024 / INT-FlashAttention
  ☆83Updated 10 months ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆41Updated last year
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆119Updated 7 months ago
• DerrickYLJ / TidalDecode
  [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
  ☆49Updated 4 months ago
• DataStates / datastates-llm
  LLM checkpointing for DeepSpeed/Megatron
  ☆22Updated 3 weeks ago
• SymbioticLab / Oobleck
  A resilient distributed training framework
  ☆96Updated last year
• merrymercy / Awesome-Efficient-LLM
  A curated list for Efficient Large Language Models
  ☆11Updated last year
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆135Updated 6 months ago