Alternatives and similar repositories for mfu_calculation:

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

• feifeibear / DPSKV3MFU
  Estimate MFU for DeepSeekV3
  ☆23Updated 4 months ago
• infinigence / FlashOverlap
  A lightweight design for computation-communication overlap.
  ☆67Updated last week
• feifeibear / Odysseus-Transformer
  Odysseus: Playground of LLM Sequence Parallelism
  ☆69Updated 10 months ago
• flashinfer-ai / cutlass-viz
  ☆57Updated last week
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆80Updated 3 weeks ago
• InternLM / turbomind
  ☆84Updated last month
• microsoft / chunk-attention
  ☆74Updated 2 weeks ago
• LeiWang1999 / AutoGPTQ.tvm
  GPTQ inference TVM kernel
  ☆38Updated last year
• MayDomine / Seq1F1B
  Sequence-level 1F1B schedule for LLMs.
  ☆17Updated 11 months ago
• kwai / Megatron-Kwai
  [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…
  ☆53Updated 9 months ago
• ademeure / DeeperGEMM
  DeeperGEMM: crazy optimized version
  ☆68Updated this week
• feifeibear / ChituAttention
  Quantized Attention on GPU
  ☆45Updated 5 months ago
• InternLM / Awesome-LLM-Training-System
  ☆35Updated 9 months ago
• hao-ai-lab / vllm-ltr
  [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank
  ☆47Updated 6 months ago
• cassiewilliam / cuda_op_benchmark
  方便扩展的Cuda算子理解和优化框架，仅用在学习使用
  ☆15Updated 10 months ago
• d-matrix-ai / keyformer-llm
  ☆53Updated last year
• feifeibear / LLMRoofline
  Compare different hardware platforms via the Roofline Model for LLM inference tasks.
  ☆99Updated last year
• li-plus / flash-preference
  Accelerate LLM preference tuning via prefix sharing with a single line of code
  ☆40Updated last week
• LoongServe / LoongServe
  ☆95Updated 5 months ago
• zhuohan123 / terapipe
  ☆72Updated 4 years ago
• fanshiqing / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆120Updated 4 months ago
• WukLab / preble
  Stateful LLM Serving
  ☆65Updated last month
• tgale96 / grouped_gemm
  PyTorch bindings for CUTLASS grouped GEMM.
  ☆88Updated last week
• thu-pacman / FasterMoE
  ☆82Updated 3 years ago
• microsoft / nnscaler
  nnScaler: Compiling DNN models for Parallel Training
  ☆109Updated last week
• DD-DuDa / BitDecoding
  A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.
  ☆34Updated 2 weeks ago
• AlibabaPAI / FLASHNN
  ☆93Updated 7 months ago
• alibaba / easydist
  Automated Parallelization System and Infrastructure for Multiple Ecosystems
  ☆78Updated 5 months ago
• hao-ai-lab / MuxServe
  ☆59Updated 10 months ago
• microsoft / ParrotServe
  [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable
  ☆155Updated 7 months ago