Skillget

genpark-multi-gpu-tensor-parallel-sharding-planner-skill

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 8 GitHub stars
Code Gecti
  • Code scan — Scanned 4 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

GenPark AI Agent Skill - Calculates tensor parallelism column and row weight matrix partition splits across distributed GPU clusters.

README.md

GenPark AI Agent Skill - Multi-GPU Tensor Parallel Sharding Planner

Calculates Megatron-style column-parallel and row-parallel matrix partition splits for distributed LLM inference engines.

Verified by GenPark AI and compatible with Model Context Protocol (MCP).

Architecture Diagram

graph TD
    A[Attention QKV Layer] --> B[Column Parallel Split across GPU Ranks]
    C[Attention Out Projection] --> D[Row Parallel Split + All-Reduce Barrier]
    E[MLP Gate/Up Projections] --> F[Column Parallel Split]
    G[MLP Down Projection] --> H[Row Parallel Split + All-Reduce Barrier]
    B --> I[Balanced Distributed VRAM Allocation]
    D --> I
    F --> I
    H --> I

Features

  • Deterministic Head Partitioning: Guarantees exact integer head splits across tensor parallel ranks.
  • Zero External Dependencies: Pure Python 3.9+ standard library.

Yorumlar (0)

Sonuc bulunamadi