Alternatives and similar repositories for ByteMLPerf

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

• OpenPPL / ppl.llm.kernel.cuda
  ☆152Updated 10 months ago
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆116Updated 6 months ago
• AlibabaPAI / torchacc
  PyTorch distributed training acceleration framework
  ☆53Updated 3 months ago
• bytedance / byteir
  A model compilation solution for various hardware
  ☆456Updated 3 months ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆188Updated last month
• OpenPPL / ppl.nn.llm
  ☆140Updated last year
• flagos-ai / FlagCX
  ☆131Updated this week
• zartbot / shallowsim
  DeepSeek-V3/R1 inference performance simulator
  ☆168Updated 8 months ago
• OpenPPL / ppl.llm.serving
  ☆130Updated 11 months ago
• antgroup / glake
  GLake: optimizing GPU memory management and IO transmission.
  ☆491Updated 8 months ago
• reed-lau / cute-gemm
  ☆149Updated 3 weeks ago
• xlite-dev / HGEMM
  ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
  ☆134Updated 6 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆119Updated last year
• microsoft / mscclpp
  MSCCL++: A GPU-driven communication stack for scalable AI applications
  ☆437Updated this week
• AlibabaPAI / FLASHNN
  ☆102Updated last year
• Yinghan-Li / YHs_Sample
  Yinghan's Code Sample
  ☆358Updated 3 years ago
• vllm-project / flash-attention
  Fast and memory-efficient exact attention
  ☆102Updated last week
• DeepLink-org / DLOP-Bench
  A benchmark suited especially for deep learning operators
  ☆42Updated 2 years ago
• Cambricon / triton-linalg
  Development repository for the Triton-Linalg conversion
  ☆204Updated 9 months ago
• MARD1NO / CUDA-PPT
  ☆113Updated 7 months ago
• AyakaGEMM / Hands-on-GEMM
  ☆144Updated last year
• nicolaswilde / cuda-tensorcore-hgemm
  ☆156Updated 11 months ago
• alibaba / TePDist
  TePDist (TEnsor Program DISTributed) is an HLO-level automatic distributed system for DL models.
  ☆97Updated 2 years ago
• DD-DuDa / Cute-Learning
  Examples of CUDA implementations by Cutlass CuTe
  ☆254Updated 5 months ago
• NVIDIA / nvbandwidth
  A tool for bandwidth measurements on NVIDIA GPUs.
  ☆571Updated 7 months ago
• OpenPPL / ppl.pmx
  ☆60Updated last year
• Cambricon / torch_mlu
  ☆46Updated 8 months ago
• bytedance / ByteTransformer
  optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
  ☆477Updated last year
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆444Updated 6 months ago
• flagos-ai / flagtree
  FlagTree is a unified compiler for multiple AI chips, which is forked from triton-lang/triton.
  ☆137Updated this week