Modified
This report provides a definitive, actionable, and unambiguous guide for migrating the Hierarchical Reasoning Model (HRM) to ROCm, specifically targeting AMD MI300X GPUs. All previous uncertainties and 'if' statements have been resolved to provide clear instructions for developers.
Current CUDA Dependencies:
The README.md explicitly outlines the installation of CUDA and PyTorch with CUDA support, along with FlashAttention, which is a CUDA-dependent library.
| #!/usr/bin/env python3 | |
| # -*- coding: utf-8 -*- | |
| """ | |
| pr-capture: A CLI tool to capture GitHub PR data into a comprehensive markdown file. | |
| """ | |
| import argparse | |
| from datetime import datetime | |
| import json |
| #!/bin/bash | |
| # zip_project.sh - Zip up source and documentation files from a Git repo, | |
| # excluding .git, .venv, and anything in .gitignore. Use --help for options. | |
| # | |
| # Usage: | |
| # ./zip_project.sh [--output FILE] [--verbose] [--filter [REGEX]] [--exclude REGEX] [--help] | |
| # | |
| # Options: | |
| # -o, --output FILE Name of the output zip file (default: project_bundle.zip) | |
| # -v, --verbose Print verbose output |
| import argparse | |
| import os | |
| import re | |
| from collections import defaultdict | |
| from typing import List, Set, Tuple | |
| import requests | |
| from packaging.version import Version, InvalidVersion | |
| # --------------------------------------------------------------------------- |
| #!/usr/bin/env bash | |
| # Generates 10-slot wallpapper solar JSONs from 6-stage image sets | |
| set -euo pipefail | |
| DIR="/Users/Shared/Wallpapers/WaterWays_Processed" | |
| cd "$DIR" || { echo "bad path: $DIR"; exit 1; } | |
| # 10-stage full-day solar path: altitude (°) and azimuth (°) | |
| ALT=(60 40 20 5 -5 -15 -5 5 20 40) # noon to night and back |
| import os | |
| import json | |
| import requests | |
| from typing import Dict, List, Any, Optional | |
| from smolagents.tools import Tool | |
| class BraveSearchTool(Tool): | |
| """Tool for interacting with the Brave Search API within the smolagents framework.""" | |
| name = "brave_search" |
| git clone https://huggingface.co/sail/Sailor2-1B-Chat | |
| Cloning into 'Sailor2-1B-Chat'... | |
| remote: Enumerating objects: 39, done. | |
| remote: Counting objects: 100% (36/36), done. | |
| remote: Compressing objects: 100% (36/36), done. | |
| remote: Total 39 (delta 14), reused 0 (delta 0), pack-reused 3 (from 1) | |
| Unpacking objects: 100% (39/39), 2.02 MiB | 2.26 MiB/s, done. | |
| Filtering content: 100% (2/2), 1.85 GiB | 14.92 MiB/s, done. | |
| ./convert_hf_to_gguf.py --outfile $HF/Sailor2-1B-Chat_bf16.gguf --outtype bf16 $HF/Sailor2-1B-Chat |
| #!/bin/bash | |
| # Check if at least one argument is provided | |
| if [ "$#" -lt 1 ]; then | |
| echo "Usage: $0 <image> [--report-file <file>] [--verbose]" | |
| exit 1 | |
| fi | |
| # Parse arguments | |
| IMAGE="" |
| from collections import namedtuple | |
| import contextlib | |
| import json | |
| import llama_cpp | |
| import logging | |
| import math | |
| import multiprocessing as mp | |
| import numpy as np | |
| import optuna | |
| import os |
| vram llama3.1:8b-instruct-q8_0 --verbose | |
| VERBOSE: Default fits value from sysctl: 40.0 GB | |
| VERBOSE: Quant value for llama3.1:8b-instruct-q8_0: Q8_0 | |
| VERBOSE: VRAM nth for llama3.1:8b-instruct-q8_0: 131072 | |
| VERBOSE: Running gollama -vram for llama3.1:8b-instruct-q8_0 with fits=40.0 GB | |
| VERBOSE: VRAM output header, labels, and rows gathered | |
| VERBOSE: Quant row: | Q8_0 | 8.50 | 9.1 | 10.9 | 13.4(12.4,11.9) | 18.4(16.4,15.4) | 28.3(24.3,22.3) | 48.2(40.2,36.2) | | |
| VERBOSE: Max A: 28.3 at 64K | |
| VERBOSE: Max B: 24.3 at 64K | |
| VERBOSE: Max C: 36.2 at 128K |