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
  ☆150Updated 7 months ago
• OpenPPL / ppl.nn.llm
  ☆140Updated last year
• OpenPPL / ppl.llm.serving
  ☆128Updated 7 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
• bytedance / byteir
  A model compilation solution for various hardware
  ☆443Updated this week
• AlibabaPAI / torchacc
  PyTorch distributed training acceleration framework
  ☆51Updated last week
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆155Updated last week
• FlagOpen / FlagCX
  ☆84Updated last week
• FlagTree / flagtree
  FlagTree is a unified compiler for multiple AI chips, which is forked from triton-lang/triton.
  ☆72Updated this week
• reed-lau / cute-gemm
  ☆130Updated 8 months ago
• vllm-project / flash-attention
  Fast and memory-efficient exact attention
  ☆87Updated last week
• OpenPPL / CuAssembler
  An unofficial cuda assembler, for all generations of SASS, hopefully ：）
  ☆83Updated 2 years ago
• zartbot / shallowsim
  DeepSeek-V3/R1 inference performance simulator
  ☆165Updated 4 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆111Updated last year
• antgroup / glake
  GLake: optimizing GPU memory management and IO transmission.
  ☆473Updated 4 months ago
• alibaba / TePDist
  TePDist (TEnsor Program DISTributed) is an HLO-level automatic distributed system for DL models.
  ☆95Updated 2 years ago
• AlibabaPAI / FLASHNN
  ☆97Updated 11 months ago
• Yinghan-Li / YHs_Sample
  Yinghan's Code Sample
  ☆344Updated 3 years ago
• microsoft / mscclpp
  MSCCL++: A GPU-driven communication stack for scalable AI applications
  ☆399Updated this week
• OpenPPL / ppl.pmx
  ☆59Updated 9 months ago
• nicolaswilde / cuda-tensorcore-hgemm
  ☆150Updated 7 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
• Cambricon / triton-linalg
  Development repository for the Triton-Linalg conversion
  ☆193Updated 6 months ago
• ColfaxResearch / cfx-article-src
  ☆135Updated 3 months ago
• DD-DuDa / Cute-Learning
  Examples of CUDA implementations by Cutlass CuTe
  ☆219Updated last month
• DeepLink-org / DLOP-Bench
  A benchmark suited especially for deep learning operators
  ☆42Updated 2 years ago
• microsoft / vattention
  Dynamic Memory Management for Serving LLMs without PagedAttention
  ☆407Updated 2 months ago
• apache / tvm-rfcs
  A home for the final text of all TVM RFCs.
  ☆105Updated 10 months ago
• microsoft / triton-shared
  Shared Middle-Layer for Triton Compilation
  ☆268Updated last week
• AyakaGEMM / Hands-on-GEMM
  ☆138Updated last year