Alternatives and similar repositories for DIOPI

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

• DeepLink-org / deeplink.framework
  ☆69Updated 9 months ago
• OpenPPL / ppl.llm.serving
  ☆128Updated 8 months ago
• OpenPPL / ppl.llm.kernel.cuda
  ☆150Updated 7 months ago
• OpenPPL / ppl.nn.llm
  ☆140Updated last year
• antgroup / glake
  GLake: optimizing GPU memory management and IO transmission.
  ☆477Updated 5 months ago
• FlagOpen / FlagGems
  FlagGems is an operator library for large language models implemented in the Triton Language.
  ☆655Updated this week
• DeepLink-org / DLOP-Bench
  A benchmark suited especially for deep learning operators
  ☆42Updated 2 years ago
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆105Updated 3 months ago
• bytedance / ByteMLPerf
  AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…
  ☆257Updated last week
• Tencent / KsanaLLM
  ☆483Updated 2 weeks ago
• harleyszhang / llm_counts
  llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
  ☆103Updated last month
• AlibabaPAI / torchacc
  PyTorch distributed training acceleration framework
  ☆51Updated last week
• AyakaGEMM / Hands-on-GEMM
  ☆138Updated last year
• alibaba / rtp-llm
  RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
  ☆838Updated 3 weeks ago
• LLMServe / DistServe
  Disaggregated serving system for Large Language Models (LLMs).
  ☆669Updated 4 months ago
• Cambricon / triton-linalg
  Development repository for the Triton-Linalg conversion
  ☆193Updated 6 months ago
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆61Updated last year
• DD-DuDa / Cute-Learning
  Examples of CUDA implementations by Cutlass CuTe
  ☆219Updated last month
• alibaba / TePDist
  TePDist (TEnsor Program DISTributed) is an HLO-level automatic distributed system for DL models.
  ☆95Updated 2 years ago
• bytedance / byteir
  A model compilation solution for various hardware
  ☆443Updated this week
• OpenPPL / ppl.pmx
  ☆59Updated 9 months ago
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆346Updated last week
• CalebDu / Awesome-Cute
  ☆100Updated 3 months ago
• reed-lau / cute-gemm
  ☆130Updated 8 months ago
• FlagOpen / FlagCX
  ☆84Updated last week
• bytedance / ByteTransformer
  optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
  ☆475Updated last year
• ifromeast / cuda_learning
  learning how CUDA works
  ☆304Updated 5 months ago
• KnowingNothing / MatmulTutorial
  A Easy-to-understand TensorOp Matmul Tutorial
  ☆372Updated 11 months ago
• ConnollyLeon / awesome-Auto-Parallelism
  A baseline repository of Auto-Parallelism in Training Neural Networks
  ☆144Updated 3 years ago
• madsys-dev / deepseekv2-profile
  ☆146Updated 5 months ago