Alternatives and similar repositories for LLMRoofline

Users that are interested in LLMRoofline are comparing it to the libraries listed below

• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆87Updated last month
• InternLM / turbomind
  ☆86Updated 2 months ago
• madsys-dev / deepseekv2-profile
  ☆141Updated 3 months ago
• AlibabaPAI / FLASHNN
  ☆96Updated 9 months ago
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆55Updated 10 months ago
• OpenPPL / ppl.llm.serving
  ☆127Updated 5 months ago
• microsoft / chunk-attention
  ☆77Updated 2 months ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆53Updated last week
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆125Updated 5 months ago
• thu-pacman / SmartMoE-AE
  ATC23 AE
  ☆45Updated 2 years ago
• OpenPPL / ppl.nn.llm
  ☆139Updated last year
• thunlp / Seq1F1B
  Sequence-level 1F1B schedule for LLMs.
  ☆27Updated 3 weeks ago
• flashinfer-ai / cutlass-viz
  ☆60Updated last month
• zartbot / shallowsim
  DeepSeek-V3/R1 inference performance simulator
  ☆148Updated 2 months ago
• ModelTC / awesome-lm-system
  Summary of system papers/frameworks/codes/tools on training or serving large model
  ☆57Updated last year
• Ascend / torchair
  ☆14Updated this week
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆141Updated last week
• zhaochenyang20 / ModelServer
  Efficient, Flexible, and Highly Fault-Tolerant Model Service Management Based on SGLang
  ☆53Updated 7 months ago
• vllm-project / flash-attention
  Fast and memory-efficient exact attention
  ☆74Updated this week
• OpenPPL / ppl.llm.kernel.cuda
  ☆148Updated 5 months ago
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆79Updated last month
• tlc-pack / libflash_attn
  Standalone Flash Attention v2 kernel without libtorch dependency
  ☆110Updated 9 months ago
• 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.
  ☆38Updated last week
• WukLab / preble
  Stateful LLM Serving
  ☆73Updated 3 months ago
• Victarry / PP-Schedule-Visualization
  Pipeline Parallelism Emulation and Visualization
  ☆42Updated last week
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆92Updated 3 weeks ago
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆163Updated 9 months ago
• AlibabaPAI / torchacc
  PyTorch distributed training acceleration framework
  ☆49Updated 4 months ago
• luliyucoordinate / cute-flash-attention
  Implement Flash Attention using Cute.
  ☆87Updated 6 months ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆69Updated last month