Alternatives and similar repositories for LLMRoofline

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

• madsys-dev / deepseekv2-profile
  ☆145Updated 5 months ago
• InternLM / turbomind
  ☆92Updated 4 months ago
• AlibabaPAI / FLASHNN
  ☆97Updated 11 months ago
• OpenPPL / ppl.llm.serving
  ☆128Updated 8 months ago
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆104Updated 3 months ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆155Updated last week
• LLMServe / SwiftTransformer
  High performance Transformer implementation in C++.
  ☆129Updated 7 months ago
• vllm-project / flash-attention
  Fast and memory-efficient exact attention
  ☆87Updated last week
• microsoft / chunk-attention
  ☆78Updated 4 months ago
• InternLM / Awesome-LLM-Training-System
  ☆43Updated last year
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆61Updated last year
• OpenPPL / ppl.llm.kernel.cuda
  ☆150Updated 7 months ago
• WukLab / preble
  Stateful LLM Serving
  ☆81Updated 5 months ago
• AlibabaResearch / flash-llm
  Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity
  ☆217Updated last year
• OpenPPL / ppl.nn.llm
  ☆140Updated last year
• thu-pacman / SmartMoE-AE
  ATC23 AE
  ☆46Updated 2 years ago
• flashinfer-ai / cutlass-viz
  ☆61Updated 4 months ago
• PKU-SEC-Lab / HybriMoE
  [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
  ☆66Updated 2 months ago
• sgl-project / SpecForge
  Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
  ☆313Updated last week
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆100Updated 3 months ago
• tlc-pack / cutlass_fpA_intB_gemm
  A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer
  ☆94Updated 2 weeks ago
• tile-ai / tilescale
  Tile-based language built for AI computation across all scales
  ☆46Updated this week
• CalebDu / Awesome-Cute
  ☆98Updated 3 months ago
• LoongServe / LoongServe
  ☆113Updated 9 months ago
• shishishu / LLM-Inference-Acceleration
  LLM Inference with Deep Learning Accelerator.
  ☆49Updated 7 months ago
• stepfun-ai / StepMesh
  ☆279Updated last week
• 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.
  ☆40Updated 2 months ago
• Bruce-Lee-LY / flash_attention_inference
  Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.
  ☆40Updated 5 months ago
• AlibabaPAI / torchacc
  PyTorch distributed training acceleration framework
  ☆51Updated last week
• d-matrix-ai / keyformer-llm
  ☆54Updated last year