davidcastagnetoa/skills
fp16_int8_quantization
Cuantización de modelos ML a FP16/INT8 para reducir memoria y acelerar inferencia en el pipeline KYC
Installation
npx skills add https://github.com/davidcastagnetoa/skills
Similar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying mode…
765 installsHalf-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/…
752 installsActivation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accu…
750 installsGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying mode…
385 installsActivation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accu…
310 installsHalf-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/…
291 installsAlso in this package
Other skills from davidcastagnetoa/skills · top by installs.
npx skills add https://github.com/davidcastagnetoa/skills
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Repository health
main
History
- First seen on skills.sh
- First recorded snapshot · 12 installs