Alternatives and similar repositories for FlagPerf

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

• antgroup / glake
  GLake: optimizing GPU memory management and IO transmission.
  ☆463Updated 2 months ago
• FlagOpen / FlagScale
  FlagScale is a large model toolkit based on open-sourced projects.
  ☆280Updated this week
• OpenPPL / ppl.llm.serving
  ☆127Updated 5 months ago
• pcg-mlp / KsanaLLM
  ☆332Updated 4 months ago
• FlagOpen / FlagGems
  FlagGems is an operator library for large language models implemented in the Triton Language.
  ☆546Updated this week
• alibaba / rtp-llm
  RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
  ☆777Updated 2 weeks ago
• modelscope / dash-infer
  DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …
  ☆253Updated this week
• zhihu / ZhiLight
  A highly optimized LLM inference acceleration engine for Llama and its variants.
  ☆890Updated 2 weeks ago
• bytedance / ByteMLPerf
  AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…
  ☆239Updated 2 weeks ago
• OpenPPL / ppl.nn.llm
  ☆138Updated last year
• LLMServe / DistServe
  Disaggregated serving system for Large Language Models (LLMs).
  ☆601Updated last month
• DeepLink-org / DIOPI
  ☆70Updated 6 months ago
• DeepLink-org / deeplink.framework
  ☆67Updated 7 months ago
• bytedance / ByteTransformer
  optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
  ☆473Updated last year
• sgl-project / sgl-learning-materials
  Materials for learning SGLang
  ☆424Updated last week
• aliyun / SimAI
  ☆525Updated 3 weeks ago
• OpenPPL / ppl.pmx
  ☆58Updated 6 months ago
• FlagOpen / FlagAttention
  A collection of memory efficient attention operators implemented in the Triton language.
  ☆271Updated 11 months ago
• OpenPPL / ppl.llm.kernel.cuda
  ☆148Updated 4 months ago
• alibaba / EasyParallelLibrary
  Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.
  ☆267Updated 2 years ago
• Qcompiler / MIXQ
  MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization by Online Prediction
  ☆89Updated 7 months ago
• FlagOpen / FlagCX
  ☆60Updated this week
• DeepLink-org / AIChipBenchmark
  ☆26Updated last month
• madsys-dev / deepseekv2-profile
  ☆137Updated 2 months ago
• AlibabaPAI / torchacc
  PyTorch distributed training acceleration framework
  ☆49Updated 3 months ago
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆100Updated last year
• infinigence / Semi-PD
  A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
  ☆80Updated 2 weeks ago
• sail-sg / zero-bubble-pipeline-parallelism
  Zero Bubble Pipeline Parallelism
  ☆395Updated 3 weeks ago
• AlibabaPAI / llumnix
  Efficient and easy multi-instance LLM serving
  ☆420Updated this week
• zartbot / shallowsim
  DeepSeek-V3/R1 inference performance simulator
  ☆134Updated 2 months ago