A simple calculation for LLM MFU.
☆78Sep 10, 2025Updated 9 months ago
Alternatives and similar repositories for mfu_calculation
Users that are interested in mfu_calculation are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 💻 Terminal-Agent with Human-in-the-Loop Learning☆40Jan 16, 2026Updated 5 months ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆308May 1, 2025Updated last year
- A dynamic binary instrumentation tool for tracing and analyzing CUDA kernel instructions.☆69Jul 1, 2026Updated last week
- parser script to process pytorch autograd profiler result, convert json file to excel.☆15Oct 8, 2019Updated 6 years ago
- ☆160Mar 5, 2026Updated 4 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆34Nov 29, 2024Updated last year
- DELTA-pytorch：DELTA: Dynamically Optimizing GPU Memory beyond Tensor Recomputation☆12Apr 16, 2024Updated 2 years ago
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆32May 12, 2026Updated last month
- A Top-Down Profiler for GPU Applications☆23Feb 29, 2024Updated 2 years ago
- ☆134Nov 11, 2024Updated last year
- LLVM/MLIR based compiler instrumentation of AMD GPU kernels☆21Jul 13, 2025Updated 11 months ago
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆106Apr 7, 2026Updated 3 months ago
- Paper reading and discussion notes, covering AI frameworks, distributed systems, cluster management, etc.☆68Mar 4, 2026Updated 4 months ago
- Course repository for the Spring 2023 COMP664 course "Deep Learning" at UNC☆14Apr 17, 2023Updated 3 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆123May 19, 2025Updated last year
- Here are my personal paper reading notes (including machine learning systems, AI infrastructure, and other interesting stuffs).☆207Updated this week
- Framework to reduce autotune overhead to zero for well known deployments.☆101Sep 19, 2025Updated 9 months ago
- All-in-one benchmarking platform for evaluating LLM.☆15Nov 12, 2025Updated 7 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆117Mar 20, 2025Updated last year
- Distributed Compiler based on Triton for Parallel Systems☆1,476Jun 25, 2026Updated 2 weeks ago
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- Triton kernels for Flux☆23Jul 7, 2025Updated last year
- DeepSeek-V3/R1 inference performance simulator☆195Mar 27, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆58Nov 20, 2024Updated last year
- Vortex: Programmable Sparse Attention for Agents as Algorithm Designers☆65Jun 24, 2026Updated 2 weeks ago
- Build a feature-less eBPF vm on eBPF, just for fun.☆16Mar 10, 2024Updated 2 years ago
- Source code for our AAAI'22 paper 《From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression》☆25Dec 15, 2021Updated 4 years ago
- ☆119May 10, 2026Updated last month
- LLM4HWDesign Starting Toolkit☆19Oct 4, 2024Updated last year
- iptables-trace is an eBPF enhanced iptables-TRACE alternative iptables TRACE. GPL-3.0 license☆14Feb 3, 2025Updated last year
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated 11 months ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆58May 3, 2026Updated 2 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Official Repo for SwS: A Weakness-driven Problem Synthesis Framework in RL for LLM Reasoning☆41Nov 11, 2025Updated 7 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆267Nov 18, 2024Updated last year
- Website for Artifact Evaluation at EuroSys, SOSP, OSDI, ATC☆52Updated this week
- ☆24Oct 10, 2025Updated 8 months ago
- 使用VC检测车道线（曲线）☆10Apr 23, 2018Updated 8 years ago
- ☆212Updated this week
- ☆10Sep 4, 2021Updated 4 years ago