R_REDDYX.XYZ
AIRust★ 238⑂ 29 forks

giannisanni/pulsar

PULSAR — ULTRAFAST MOE INFERENCE

Pulsar — an SSD-streaming engine for giant MoE models on Rust+CUDA.

// KEY FEATURES

  • Measures PCIe bandwidth and places attention and experts.
  • Automatic multi-GPU without settings.
  • Runs on Rust + CUDA, delivering 2-7 tok/s on a 16 GB GPU.
#cuda#gguf#glm#inference-engine#llm#local-llm#mixture-of-experts#moe#multi-gpu#quantization#rust#ssd-streaming
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

ADHD — Skill for Coding Agents★ 238AnyKB: Private RAG Agent★ 238AI ADVISOR FOR TRADERS★ 238AI Team for Code Review★ 238GPT-ALL-STAR — AI TEAM WRITES CODE★ 238BEACON-SKILL: AGENT PINGS★ 238

← FULL CATALOG

giannisanni/pulsar — Pulsar — Ultrafast Moe Inference