AIPython★ 501⑂ 33 forksApache-2.0
OmniJev/Flide
FLIDE: INSTANT DECISION INFERENCE
Flide is a decision model inference engine with CUDA support. Provides deterministic inference for Gemma and other models in microseconds. Ideal for AI agents requiring speed.
// KEY FEATURES
- Deterministic CUDA inference in microseconds
- Supports Gemma and custom decision models
- Python API for AI agent and pipeline integration
- 260 GitHub stars, pure Python without heavy deps
#ai-agents#cuda#decision-making#deterministic-inference#gemma#inference-engine#jev#kv-cache#large-language-models#linear-attention#llm#llm-agents
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