accuracy-safe-quantization
google-ai-edge
Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when…
ResearchClaude Code
431GitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “quantization”
1–2 / 2
More filters · 1
Results: 2
Latest information is temporarily unavailable. Showing previously saved content.
on-device-verification
google-ai-edge
Prove a converted or quantized LiteRT model on the actual device via the CompiledModel API - confirm GPU residency, compare device output against the source model, and d…
416GitHub
External platform skills
Browse external directory →Owner-curated external sources. Not filtered by the scores or compatibility controls above; excluded from GitHub rankings and automatic installation.
No external entries match this query.