菜单
NVIDIA Model Optimizer — quantization, pruning, distillation, and speculative decoding for accelerating LLMs, diffusion models, and vision models on NVIDIA GPUs.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/mkurman/zorai --skill nvidia-model-optimizer命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Use when provisioning Prime Intellect GPU compute, managing pods/disks/sandboxes, running hosted RL training via prime lab, installing or publishing RL environments, or exposing local services via Prime Tunnel. Covers the `prime` CLI (PyPI: prime) for all Prime Intellect platform operations.
Shared Python package for Science Skills, currently containing http_client -- a unified HTTP client with rate limiting, retries, and exponential backoff. Not a standalone agent skill. Do not invoke directly.
Retrieve and analyze AlphaFold predicted structures for a protein. Use when the user provides a specific UniProt Accession ID and wants structural confidence metrics (pLDDT), domain boundary analysis, or disorder assessment. Do not use if the user only has a protein name, gene name, or amino acid sequence — ask for a UniProt ID first.
基于 SOC 职业分类
正在显示 SKILL.md
| name | nvidia-model-optimizer |
| description | NVIDIA Model Optimizer — quantization, pruning, distillation, and speculative decoding for accelerating LLMs, diffusion models, and vision models on NVIDIA GPUs. |
| tags | ["nvidia-model-optimizer","quantization","pruning","distillation","modelopt","tensorrt","zorai"] |
NVIDIA Model Optimizer provides state-of-the-art model optimization techniques — quantization (FP8, INT4, NVFP4), pruning, knowledge distillation, and speculative decoding — for models deployable on TensorRT-LLM, SGLang, and vLLM.
uv pip install nvidia-modelopt
import modelopt.torch.quantization as mtq
# FP8 post-training quantization
quant_cfg = mtq.FP8_DEFAULT_CFG
mtq.quantize(model, quant_cfg, forward_loop=calib_loop)
# Export for TensorRT-LLM
from modelopt.torch.export import export_tensorrt_llm_checkpoint
export_tensorrt_llm_checkpoint(model, "model.pt", dtype="fp8")
import modelopt.torch.pruning as mtp
import modelopt.torch.distill as mtd
# Prune
pruned = mtp.prune(model, ratio=0.3, structure="2:4_sparse")
# Distill
teacher = load_teacher_model()
student = mtd.distill(student_model, teacher, kal="logit", alpha=0.5)