R_REDDYX.XYZ
AIC++★ 1,586⑂ 198 forksApache-2.0

uccl-project/uccl

UCCL: GPU Communication at Max

A fast library for efficient data exchange between GPUs: collective operations, P2P, and inference acceleration.

// KEY FEATURES

  • Collective and P2P operations
  • Transfer of KV cache and RL weights
  • GPU-driven routing
#ai#allreduce#amd#broadcom#collective#cuda#gpu#hpc#kvcache#llm#moe#networking
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

UZU: Powerful Engine for AI Models★ 1586AGMSG - CROSS-VENDOR MESSENGER FOR CLI-AGENTS★ 1586LLM Inference on AWS Trainium★ 1585AGENTLY: SIMPLIFYING GEN-AI DEVELOPMENT★ 1584OPENCLAW-TERMUX: AI ON YOUR PHONE★ 1588OPENSERP — AI SEARCH API SELF-HOSTED★ 1584

← FULL CATALOG

uccl-project/uccl — UCCL: GPU Communication at Max