From 8330af32c136014799b0d699d47a7bf323db82b3 Mon Sep 17 00:00:00 2001 From: Sepehr Sameni Date: Mon, 20 Jul 2026 13:22:39 +0200 Subject: [PATCH 1/4] Add link to puzzletron_v2 Signed-off-by: Sepehr Sameni --- examples/puzzletron/README.md | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/examples/puzzletron/README.md b/examples/puzzletron/README.md index 6beed07467a..722c05503e0 100644 --- a/examples/puzzletron/README.md +++ b/examples/puzzletron/README.md @@ -1,3 +1,9 @@ +# Puzzletron + +For a step-by-step tutorial on the core Puzzletron algorithm, see below. For advanced campaigns with production-scale models, +AutoModel-based distributed training, and nested models, see the [experimental Puzzletron +branch](https://github.com/NVIDIA/Model-Optimizer/tree/puzzletron_v2/examples/puzzletron). + # Puzzletron Algorithm Tutorial This tutorial demonstrates how to compress large language models using the puzzletron algorithm based on the [Puzzle paper](https://arxiv.org/abs/2411.19146). From a22d9901ad9fd74516dde2f787b307a2b27159b3 Mon Sep 17 00:00:00 2001 From: Sepehr Sameni Date: Mon, 20 Jul 2026 14:55:41 +0200 Subject: [PATCH 2/4] Update README.md Signed-off-by: Sepehr Sameni --- examples/puzzletron/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/puzzletron/README.md b/examples/puzzletron/README.md index 722c05503e0..74ff94f444a 100644 --- a/examples/puzzletron/README.md +++ b/examples/puzzletron/README.md @@ -1,7 +1,7 @@ # Puzzletron -For a step-by-step tutorial on the core Puzzletron algorithm, see below. For advanced campaigns with production-scale models, -AutoModel-based distributed training, and nested models, see the [experimental Puzzletron +For a step-by-step tutorial on the core Puzzletron algorithm, see below. For advanced settings with production-scale models, +[AutoModel](https://github.com/NVIDIA-NeMo/Automodel/)-based distributed training, and nested models, see the [experimental Puzzletron branch](https://github.com/NVIDIA/Model-Optimizer/tree/puzzletron_v2/examples/puzzletron). # Puzzletron Algorithm Tutorial From 4a435eb6c7bf361061fee327f788a930cc39fa15 Mon Sep 17 00:00:00 2001 From: Sepehr Sameni Date: Mon, 20 Jul 2026 14:56:12 +0200 Subject: [PATCH 3/4] Update README.md Signed-off-by: Sepehr Sameni --- examples/puzzletron/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/puzzletron/README.md b/examples/puzzletron/README.md index 74ff94f444a..d86150e0994 100644 --- a/examples/puzzletron/README.md +++ b/examples/puzzletron/README.md @@ -1,7 +1,7 @@ # Puzzletron -For a step-by-step tutorial on the core Puzzletron algorithm, see below. For advanced settings with production-scale models, -[AutoModel](https://github.com/NVIDIA-NeMo/Automodel/)-based distributed training, and nested models, see the [experimental Puzzletron +For a step-by-step tutorial on the core Puzzletron algorithm, see below. For advanced settings with production-scale models and +[AutoModel](https://github.com/NVIDIA-NeMo/Automodel/)-based distributed training, see the [experimental Puzzletron branch](https://github.com/NVIDIA/Model-Optimizer/tree/puzzletron_v2/examples/puzzletron). # Puzzletron Algorithm Tutorial From 7565d6816857a9315628a88b7ef7755ec2ea0005 Mon Sep 17 00:00:00 2001 From: Sepehr Sameni Date: Mon, 20 Jul 2026 15:58:38 +0200 Subject: [PATCH 4/4] Update README.md Signed-off-by: Sepehr Sameni --- examples/puzzletron/README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/examples/puzzletron/README.md b/examples/puzzletron/README.md index d86150e0994..5a5aac1fd68 100644 --- a/examples/puzzletron/README.md +++ b/examples/puzzletron/README.md @@ -1,8 +1,8 @@ # Puzzletron -For a step-by-step tutorial on the core Puzzletron algorithm, see below. For advanced settings with production-scale models and -[AutoModel](https://github.com/NVIDIA-NeMo/Automodel/)-based distributed training, see the [experimental Puzzletron -branch](https://github.com/NVIDIA/Model-Optimizer/tree/puzzletron_v2/examples/puzzletron). +For a step-by-step tutorial on the core Puzzletron algorithm, see the [Puzzletron Algorithm Tutorial](`#puzzletron-algorithm-tutorial`) below. +For advanced settings with production-scale models and [AutoModel](https://github.com/NVIDIA-NeMo/Automodel/)-based distributed training, see the [experimental Puzzletron +branch](https://github.com/NVIDIA/Model-Optimizer/tree/puzzletron_v2/examples/puzzletron/README.md). # Puzzletron Algorithm Tutorial