Skip to content
View massif-01's full-sized avatar
:octocat:
exploring
:octocat:
exploring
64 followers · 13 following

Achievements

Achievement: YOLOAchievement: Pull Sharkx3Achievement: StarstruckAchievement: Galaxy BrainAchievement: QuickdrawAchievement: Pair Extraordinairex3Achievement: Public Sponsor

Achievements

Achievement: YOLOAchievement: Pull Sharkx3Achievement: StarstruckAchievement: Galaxy BrainAchievement: QuickdrawAchievement: Pair Extraordinairex3Achievement: Public Sponsor

Highlights

Block or report massif-01

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
massif-01/README.md

Hey! Nice to see you.

Trophy

Profile 3D Contribution

Pinned Loading

  1. AuraCap AuraCap Public

    The first open-source project to use GitHub Release as a transient middleware: Turn iOS captures into structured knowledge with zero-server cost.

    Python 31 2

  2. ChatRaw ChatRaw Public

    Ultra-minimal AI chat UI: 30s deploy, macOS version; no sign-up; OpenAI-compatible; plugins/adapters.

    JavaScript 57 6

  3. ZhuLinsen/daily_stock_analysis ZhuLinsen/daily_stock_analysis Public

    LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost…

    Python 52.7k 45.7k

  4. RMinte/TianshanOS RMinte/TianshanOS Public

    TianShanOS - ESP32-S3 based Rack Management Operating System for Server Cabinet Control

    C 5 2

  5. vllm_benchmark_block_fp8 vllm_benchmark_block_fp8 Public

    Automated Triton w8a8 block FP8 kernel tuning tool for vLLM. Auto-detects model architecture, supports Qwen3-Coder-30B-A3B-Instruct-FP8/DeepSeek-V3/custom models, multi-GPU parallel tuning, and gen…

    Python 13 2

  6. benchmark_moe benchmark_moe Public

    [fixed]vLLM MoE (Mixture of Experts) model kernel performance optimization tool

    Python 8 1