LogoClawIndex
CasesSkillsAbout
LogoClawIndex

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Skills·
Cases

Meta

About·
Disclaimer·
Email·
GitHub
© 2026 ClawIndex All Rights Reserved.

Skills tagged: FP8

Browse skills that share this tag.

  • tensorrt-llm - Optimize LLM inference on NVIDIA GPUs using TensorRT-LLM
    Inference ServingTensorRT-LLMNVIDIAInference Optimization

    ★ 0 · Updated 2026-09-09

    Optimizes LLM inference performance on NVIDIA GPUs with quantization, in-flight batching, and multi-GPU scaling.

    ⚙ Generate text responses from prompts⚙ Serve models via HTTP API⚙ Quantize models to lower precision
  • tensorrt-llm - Optimizing LLM Inference with NVIDIA TensorRT
    Inference ServingTensorRT-LLMNVIDIAInference Optimization

    ★ 0 · Updated 2026-09-09

    Optimizes LLM inference on NVIDIA GPUs using quantization, in-flight batching, and multi-GPU scaling.

    ⚙ Run LLM inference⚙ Serve models via HTTP server⚙ Quantize models with FP8
  • optimizing-attention-flash - Flash Attention Optimization for Transformers
    Flash AttentionAttention OptimizationMemory EfficiencyPyTorch

    ★ 18 · Updated 2026-06-30

    Optimizes transformer attention using Flash Attention via PyTorch SDPA, flash-attn library, H100 FP8, and sliding window attention.

    ⚙ Enable Flash Attention backend⚙ Replace standard attention computation⚙ Benchmark attention speed and memory
  • miles-rl-training - Enterprise RL Training Framework
    Reinforcement LearningMoEFP8INT4

    ★ 602 · Updated 2026-05-11

    Enterprise-grade RL training framework for large MoE models with FP8/INT4 support

    ⚙ train MoE models⚙ configure FP8 training⚙ configure INT4 training
  • tensorrt-llm - TensorRT-LLM LLM Inference Optimization
    Inference ServingTensorRT-LLMNVIDIAInference Optimization

    ★ 2 · Updated 2026-03-19

    Optimizes LLM inference with NVIDIA TensorRT for high-throughput, low-latency production deployment on NVIDIA GPUs.

    ⚙ optimize LLM inference⚙ compile models with TensorRT⚙ serve models via HTTP API