From 71f171f7a8fe1406e262aadb17a33e9b80601316 Mon Sep 17 00:00:00 2001 From: nathanhubens Date: Wed, 1 Jul 2026 20:36:49 +0200 Subject: [PATCH] docs: trim ecosystem overview to the open peer packages Remove a downstream workflow package from the ecosystem table and the closing one-liner in overview.ipynb; keep fasterai / fasterbench / fasterlatency. --- nbs/overview.ipynb | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/nbs/overview.ipynb b/nbs/overview.ipynb index cdc6ad1..8766cf2 100644 --- a/nbs/overview.ipynb +++ b/nbs/overview.ipynb @@ -265,7 +265,24 @@ "cell_type": "markdown", "id": "c5xvp6sdy6d", "metadata": {}, - "source": "## The FasterAI Ecosystem\n\nfasterai is part of a family of libraries designed to make neural network optimization accessible:\n\n| Package | Purpose | When to Use |\n|---------|---------|-------------|\n| **fasterai** | Compression techniques | Pruning, sparsification, distillation, quantization during training |\n| **fasterbench** | Benchmarking | Measuring model size, speed, memory, compute, and energy |\n| **fasterlatency** | Latency prediction | Hardware-aware neural architecture search |\n| **fasterrecipes** | High-level workflows | Quick compression with sensible defaults |\n\n### Typical Workflow\n\n1. **Benchmark** your model with `fasterbench` to identify bottlenecks\n2. **Compress** using `fasterai` techniques (pruning, distillation, quantization)\n3. **Validate** compression impact with `fasterbench`\n4. **Deploy** the optimized model\n\nOr use `fasterrecipes` for one-line compression with sensible defaults!" + "source": [ + "## The FasterAI Ecosystem\n", + "\n", + "fasterai is part of a family of libraries designed to make neural network optimization accessible:\n", + "\n", + "| Package | Purpose | When to Use |\n", + "|---------|---------|-------------|\n", + "| **fasterai** | Compression techniques | Pruning, sparsification, distillation, quantization during training |\n", + "| **fasterbench** | Benchmarking | Measuring model size, speed, memory, compute, and energy |\n", + "| **fasterlatency** | Latency prediction | Hardware-aware neural architecture search |\n", + "\n", + "### Typical Workflow\n", + "\n", + "1. **Benchmark** your model with `fasterbench` to identify bottlenecks\n", + "2. **Compress** using `fasterai` techniques (pruning, distillation, quantization)\n", + "3. **Validate** compression impact with `fasterbench`\n", + "4. **Deploy** the optimized model" + ] }, { "cell_type": "markdown",