home.social

#qemu — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #qemu, aggregated by home.social.

  1. I will attend the ESA Industry Space Days next week. I would be happy to meet and discuss our #RTEMS, #Linux, #NuttX, communication, #canbus, #SpaceWire, IP cores related work. Some examples

    I arrive to Noordwijk around the lunch time on Tuesday September 15 and stay there to about 2 PM on Friday so there is lot of options to meet.

  2. Here is another in a series of attempts to divine information from #qemu's issue tracker. I think this is showing that #AI #bugpocolypse reports tend to be verbose, a lot of sanitizer reports are probably mislabelled (quite often the agent will show the failure in a sanitized build) and having a decent test case correlates well with undeclared agent use. The "normal" size of reports for each class of device in (Untagged) for any tooling or TestCase.

    #datadive #bugtracker

  3. Here is another in a series of attempts to divine information from #qemu's issue tracker. I think this is showing that #AI #bugpocolypse reports tend to be verbose, a lot of sanitizer reports are probably mislabelled (quite often the agent will show the failure in a sanitized build) and having a decent test case correlates well with undeclared agent use. The "normal" size of reports for each class of device in (Untagged) for any tooling or TestCase.

    #datadive #bugtracker

  4. Here is another in a series of attempts to divine information from #qemu's issue tracker. I think this is showing that #AI #bugpocolypse reports tend to be verbose, a lot of sanitizer reports are probably mislabelled (quite often the agent will show the failure in a sanitized build) and having a decent test case correlates well with undeclared agent use. The "normal" size of reports for each class of device in (Untagged) for any tooling or TestCase.

    #datadive #bugtracker

  5. Here is another in a series of attempts to divine information from #qemu's issue tracker. I think this is showing that #AI #bugpocolypse reports tend to be verbose, a lot of sanitizer reports are probably mislabelled (quite often the agent will show the failure in a sanitized build) and having a decent test case correlates well with undeclared agent use. The "normal" size of reports for each class of device in (Untagged) for any tooling or TestCase.

    #datadive #bugtracker

  6. Here is another in a series of attempts to divine information from #qemu's issue tracker. I think this is showing that #AI #bugpocolypse reports tend to be verbose, a lot of sanitizer reports are probably mislabelled (quite often the agent will show the failure in a sanitized build) and having a decent test case correlates well with undeclared agent use. The "normal" size of reports for each class of device in (Untagged) for any tooling or TestCase.

    #datadive #bugtracker

  7. The open-issue emotional roller coaster. 🎢

    Hooray, there's an issue for this... oh no, it's been open since 2021! Issue affects nested #qemu virtualisation with #FreeBSD: gitlab.com/qemu-project/qemu/-

  8. Как QEMU исполняет чужой код: изучаем Tiny Code Compilator изнутри

    QEMU — это не просто виртуализация с KVM. Его главная cуперсила — способность запускать программы, скомпилированные для одной архитектуры, на совершенно другом процессоре. Безо всякой поддержки со стороны хоста. Например, запустить прошивку для ARM-микроконтроллера на x86-ноутбуке. Как это работает? Под капотом QEMU скрывается JIT-компилятор под названием TCG (Tiny Code Generator). В этой статье мы разберем его устройство на практических примерах для RISC-V и посмотрим, как инструкции превращаются из одного машинного кода в другой, как формируются блоки трансляции, и зачем там нужны longjmp и цепочки блоков.

    habr.com/ru/companies/yadro/ar

    #qemu #tcg #jit

  9. #weeklyreview 24/2026

    This was a busy week. Two social events and long work days. Of course also more fiddling with tech. But it all started with the 4th

    Digital Independence Day Templin/Uckermark

    For the fourth time we met in Templin to show and tell people about alternative to big commercial technology. This time a bunch of new faces showed up and we were a total of 8 people. Its getting traction despite our lousy advertisement efforts.

    One quote from my partner in crime resonated with me especially:

    You don’t need to switch directly from Windows to Linux. Rather start replacing application by application with their open source alternative. Once you’ve replace InternetExplorer or Chrome with Firefox, MS Office with LibreOffice and Outlook with Thunderbird, you’ve likely already covered the majority of your computer use. When you then switch from Windows to Linux you’ll be met with familiar applications already.

    The 5th event will take place on July 5th in Templin again.

    Movies & Paintings

    Back on Sunday evening Berlin K2 started to watch a movie it seem to like. The story is about a woman at the end of the 18th century. She’s supposed to get a portrait of her painted by a another woman.

    The scenery looked more and more familiar the longer I watched. Eventually it struck me. One scene of that movie we’ve got as an painting from my dear friend Cristina Carrillo.

    The movie is the french “Portrait of a lady on fire” by director Céline Sciamma and it’s really good.

    Greybeard gathering

    As it was the 2nd Tuesday of the month our group of old hackers gathered again at the Pratergarten. This time it was warm enough to start sitting outside in the beer garden and in the sun. One guy joked that direct sunlight is not the right environment for hackers.

    Why greybeards you ask? Because a lot of the original male software developers of Unix (think Kernighan & Ritchie ) were sporting full beards and eventually those became grey. Funny enough in our group I’m the only one with a beard … and I’m not a hacker.

    Always quite an interesting meeting as those guys know a lot beside mere programming and computers. Learned quite some things about Taurus weapon systems this time.

    Linux to the rescue

    A friend of mine water damaged their HP Laptop. Wouldn’t boot up anymore despite the fans turning when powered on. I took out the harddrive to see if that’s still working. And it is. Got Windows 11 on it. Now while we have access to the mere files, some valuable data is still hidden inside programs and their proprietary formats.

    Unfortunately the Disk didn’t fit in own HP laptop as it’s got a different SSD connector. What I had though is a SSD-to-USB adapter. I thought it should be possible to create a virtual machine though that simulates the original Laptop to some extend and use the USB-device as it’s hard drive. The normal VM wizard didn’t lead to success so I asked Perplexity to help me create the correct QEMU/KVM call.

    And it delivered. I needed to create a software TPM device first as the original Laptop uses UEFI. After some fiddling I actually got the original OS booting up on my trusty Linux Laptop despite some 10 years hardware difference. The Documentation and explanation of the steps can be found here.

    My friend but has now bought a similar laptop as replacement. We’ll put the disc into the new Laptop and will hope that the system will just come up. Let’s see. But good to know that my approach would have worked using virtualization.

    Beer & Burgers

    On Thursday it was time for our beer & burger gathering again. This time in West Berlin … Upper Burger Grill in Charlottenburg.

    The Burger was quite OK. Not the best I ever had … but also not the worst 😉

    After the burgers we felt fancy and decided to pay the Monkey Bar a visit. That’s a quite popular bar at the moment at the end of the Bikini House Berlin. It oversees the “Zoologischer Garten” and I guess you could see the monkeys during the day.

    The view is indeed stunning. You can see over to the Gedaechtniskirche, the Bikini House and of course the Zoo. What I found most interesting was the audience. Every age group from Teenagers (I hope 16+) to people probably approaching their 80s were there. So they’re doing something right attracting such a diverse age group. Then again the Ku’damm area feels a little weird to me. Everyone seems to be pretending their rich and famous. Some surely are. Most just pretend and want to part of the hype. Also… it seems to be mostly russian speaking people nowadays in that Area.

    Elk

    This week the Version 1.0 of the alternative web client for Fediverse services named “Elk” was release. I’m hosting my own instance and are using it currently as my main Mastodon Client on the web.

    One nice notable feature (among many others) is it’s ability to compose longer threads. The compose window let’s you split your longer writings into multiple properly linked posts. I know that some people struggle with this. Many Fediverse instances have a character limit for their posts – usually 500. I’ve patched my Mastodon instance to allow 5000 characters in a single post. So if your instance has a short limit and you want to post longer texts then consider using Elk for this purpose.

    Local LLM stuff

    I’ve continued playing with my LiteLLM setup. Also finally got OpenCode configured and used Qwen3.6 with Ollama on my laptop to write me some Ansible playbooks for installing and configuring OpenCode. That worked quite well.

    I’ve also tried to calculate the cost of my Ollama setup on my Laptop at the energy price of 30ct/kWh. The M2 Max CPU/GPU seem to be able to churn out ~ 50 Tokens/s while consuming 65W. For 1M tokens it would roughly need 5.5 hours at 65W. That’s about 0,3575 kWh and thus ~ 10,7ct/1M tokens.

    Of course I build myself a benchmark tool that produces the numbers for all available models on my machine and spits out a respective config file for LiteLLM

    Full Report

    ollama-bench Results

    Date: 2026–06–15 18:28 Models: 11 Prompts: 3 Runs/prompt: 3 Max tokens: 200
    Power draw: 65W Electricity: 30 cent/kWh

    Per-Model Details

    deepseek-r1:1.5b

    MetricAverageStd DevTokens generated200—Generation speed164.58 tok/s±2.04Time to first token345 ms—Total wall time1571 ms—Energy consumed28.22 µkWh—Cost per token€0.000000042327—Cost per 1M tokens€0.0423—

    Per-run breakdown:

    RunTokensSpeed (tok/s)TTFT (ms)Energy (µkWh)Cost per token#1200159.46199858.76€0.000000088146#2200165.2113324.29€0.000000036442#3200165.7513124.19€0.000000036278#4200166.0415824.63€0.000000036946#5200165.7813324.22€0.000000036336#6200165.4413324.26€0.000000036397#7200165.3015724.71€0.000000037068#8200163.9513224.45€0.000000036668#9200164.2813424.44€0.000000036665

    embeddinggemma:latest

    No successful runs.

    gemma4:12b-mlx

    MetricAverageStd DevTokens generated200—Generation speed25.33 tok/s±1.73Time to first token441 ms—Total wall time8376 ms—Energy consumed151.04 µkWh—Cost per token€0.000000226563—Cost per 1M tokens€0.2266—

    Per-run breakdown:

    RunTokensSpeed (tok/s)TTFT (ms)Energy (µkWh)Cost per token#120029.632633169.43€0.000000254139#220025.97126141.34€0.000000212014#320025.60109143.04€0.000000214565#420024.92338151.04€0.000000226557#520024.41112149.95€0.000000224931#620024.25100150.73€0.000000226102#720024.19333155.31€0.000000232968#820024.54106149.07€0.000000223605#920024.49111149.46€0.000000224189

    glm–4.7-flash:latest

    MetricAverageStd DevTokens generated200—Generation speed49.06 tok/s±2.71Time to first token1104 ms—Total wall time5202 ms—Energy consumed93.78 µkWh—Cost per token€0.000000140672—Cost per 1M tokens€0.1407—

    Per-run breakdown:

    RunTokensSpeed (tok/s)TTFT (ms)Energy (µkWh)Cost per token#120052.427969212.82€0.000000319226#220052.5022972.97€0.000000109457#320051.7922073.76€0.000000110633#420047.7230181.17€0.000000121749#520048.6822278.23€0.000000117351#620048.0522579.28€0.000000118926#720047.8632181.28€0.000000121927#820048.2822278.84€0.000000118265#920044.2722585.67€0.000000128512

    gpt-oss:latest

    MetricAverageStd DevTokens generated190—Generation speed51.89 tok/s±5.22Time to first token1195 ms—Total wall time4883 ms—Energy consumed87.95 µkWh—Cost per token€0.000000139035—Cost per 1M tokens€0.1390—

    Per-run breakdown:

    RunTokensSpeed (tok/s)TTFT (ms)Energy (µkWh)Cost per token#120064.297670194.70€0.000000292055#220056.0432470.33€0.000000105494#320049.2035279.81€0.000000119716#416949.4638768.75€0.000000122042#520050.0838879.18€0.000000118768#614547.3339062.41€0.000000129125#720049.3442880.98€0.000000121468#820050.5940978.83€0.000000118245#919450.6540876.58€0.000000118427

    lfm2.5-thinking:latest

    MetricAverageStd DevTokens generated200—Generation speed220.08 tok/s±25.13Time to first token179 ms—Total wall time1110 ms—Energy consumed19.85 µkWh—Cost per token€0.000000029775—Cost per 1M tokens€0.0298—

    Per-run breakdown:

    RunTokensSpeed (tok/s)TTFT (ms)Energy (µkWh)Cost per token#1200254.3090330.53€0.00000004579#2200256.758115.55€0.000000023331#3200246.508116.14€0.000000024204#4200193.0210620.65€0.000000030974#5200197.348719.90€0.000000029855#6200205.028219.13€0.000000028694#7200206.7010519.39€0.000000029091#8200209.448218.75€0.000000028132#9200211.658418.60€0.000000027903

    llama3.2:1b

    MetricAverageStd DevTokens generated133—Generation speed169.33 tok/s±9.77Time to first token348 ms—Total wall time1163 ms—Energy consumed20.82 µkWh—Cost per token€0.000000046968—Cost per 1M tokens€0.0470—

    Per-run breakdown:

    RunTokensSpeed (tok/s)TTFT (ms)Energy (µkWh)Cost per token#1200155.79178555.43€0.000000083146#2200156.2716626.15€0.000000039231#3200161.4316525.39€0.000000038085#468185.091799.90€0.00000004367#5117173.1216515.21€0.000000039005#672176.9816210.30€0.000000042897#7116173.4717915.34€0.000000039682#8117169.4916515.47€0.000000039674#9107172.3616414.20€0.000000039822

    llama3.2:latest

    MetricAverageStd DevTokens generated140—Generation speed81.62 tok/s±2.52Time to first token524 ms—Total wall time2250 ms—Energy consumed40.45 µkWh—Cost per token€0.000000086673—Cost per 1M tokens€0.0867—

    Per-run breakdown:

    RunTokensSpeed (tok/s)TTFT (ms)Energy (µkWh)Cost per token#120080.353315104.81€0.00000015722#220083.2616446.41€0.000000069612#320083.5116646.32€0.000000069477#411386.1620027.37€0.000000072663#510482.3816525.83€0.000000074512#611381.1116728.21€0.000000074901#711180.1320628.79€0.000000077798#810880.2516627.35€0.000000075972#911177.4316728.94€0.000000078218

    mistral:latest

    MetricAverageStd DevTokens generated190—Generation speed36.54 tok/s±1.59Time to first token373 ms—Total wall time5595 ms—Energy consumed100.72 µkWh—Cost per token€0.000000159125—Cost per 1M tokens€0.1591—

    Per-run breakdown:

    RunTokensSpeed (tok/s)TTFT (ms)Energy (µkWh)Cost per token#120039.252688140.58€0.00000021087#220039.288393.54€0.000000140311#320035.6549102.23€0.000000153349#420035.21160105.52€0.000000158286#520035.4552102.85€0.000000154271#617335.665588.65€0.000000153722#717236.4115888.21€0.000000153854#818735.905495.07€0.000000152513#917735.995489.84€0.000000152266

    qwen3.6:35b-mlx

    MetricAverageStd DevTokens generated200—Generation speed66.81 tok/s±2.82Time to first token980 ms—Total wall time3987 ms—Energy consumed71.85 µkWh—Cost per token€0.000000107768—Cost per 1M tokens€0.1078—

    Per-run breakdown:

    RunTokensSpeed (tok/s)TTFT (ms)Energy (µkWh)Cost per token#120069.277994196.48€0.000000294719#220070.3610053.15€0.00000007972#320070.296152.49€0.000000078734#420068.6716155.50€0.000000083247#520065.4810156.97€0.000000085461#620065.106556.64€0.000000084967#720065.0016958.62€0.000000087933#820063.759858.43€0.000000087638#920063.347358.33€0.000000087495

    qwen3.6:latest

    MetricAverageStd DevTokens generated200—Generation speed57.33 tok/s±1.49Time to first token1332 ms—Total wall time4859 ms—Energy consumed87.37 µkWh—Cost per token€0.000000131056—Cost per 1M tokens€0.1311—

    Per-run breakdown:

    RunTokensSpeed (tok/s)TTFT (ms)Energy (µkWh)Cost per token#120059.589619234.39€0.000000351579#220059.6027765.84€0.000000098764#320058.2427167.18€0.000000100772#420056.8936070.31€0.000000105468#520055.6927470.08€0.000000105124#620056.1627269.55€0.000000104324#720057.0337370.38€0.000000105568#820056.9327168.61€0.000000102909#920055.8727470.00€0.000000104995

    Model Comparison

    ModelSpeed (tok/s)TTFT (ms)Energy (µkWh)Cost/token (EUR)Cost/1M tokens (EUR)deepseek-r1:1.5b164.5834528.22€0.000000042327€0.0423embeddinggemma:latest—————gemma4:12b-mlx25.33441151.04€0.000000226563€0.2266glm–4.7-flash:latest49.06110493.78€0.000000140672€0.1407gpt-oss:latest51.89119587.95€0.000000139035€0.1390lfm2.5-thinking:latest220.0817919.85€0.000000029775€0.0298llama3.2:1b169.3334820.82€0.000000046968€0.0470llama3.2:latest81.6252440.45€0.000000086673€0.0867mistral:latest36.54373100.72€0.000000159125€0.1591qwen3.6:35b-mlx66.8198071.85€0.000000107768€0.1078qwen3.6:latest57.33133287.37€0.000000131056€0.1311

    Ranked by generation speed:
    1. lfm2.5-thinking:latest — 220.08 tok/s
    2. llama3.2:1b — 169.33 tok/s
    3. deepseek-r1:1.5b — 164.58 tok/s
    4. llama3.2:latest — 81.62 tok/s
    5. qwen3.6:35b-mlx — 66.81 tok/s
    6. qwen3.6:latest — 57.33 tok/s
    7. gpt-oss:latest — 51.89 tok/s
    8. glm–4.7-flash:latest — 49.06 tok/s
    9. mistral:latest — 36.54 tok/s
    10. gemma4:12b-mlx — 25.33 tok/s

    #burger #did #enEN #food #Linux #LiteLLM #QEMU #Uckermark #weekly #weeklyreview
  10. Эмулятор Qemu | Установка и настройка

    В данной статье я расскажу о том, как работать с Qemu. Научимся запускать операционные системы без необходимости делать загрузочные флешки. Разберёмся на базовом уровне с настройками и опциями данного эмулятора.

    habr.com/ru/articles/1028038/

    #bashскрипт #emulator #qemu #qemukvm

  11. [Перевод] Как я убедил виртуальную машину, что у неё есть кулер

    Зачем вообще этим заморачиваться? Некоторые образцы malware выполняют различные проверки, чтобы определить, запущены ли они в виртуальной машине. Один из самых частых способов — проверка наличия определённых аппаратных компонентов, обычно не эмулируемых в виртуальных средах. Один из таких компонентов — кулер процессора . Например, malware может проверять наличие кулера процессора, поискав в WMI класс Win32_Fan : wmic path Win32_Fan get * Они делают это, чтобы не запускаться в виртуальных машинах, усложнив таким образом процесс анализа для исследователей безопасности. Зловредное ПО может определять, запущено ли оно в виртуальной машине, множеством разных способов. Есть различные классы WMI, позволяющие обнаружит присутствие виртуальной машины, например, Win32_CacheMemory , Win32_VoltageProbe и множество других . В этом посте я расскажу о кулере процессора. Мне просто понравилась идея убедить виртуальную машину, что он у неё есть. Однако такой же подход можно применить к другим аппаратным компонентам и классам WMI.

    habr.com/ru/articles/923314/

    #виртуальные_машины #malware #xen #qemu #qemukvm

  12. Автоматизируем создание cloud native образов: пошаговая инструкция

    Всем привет! С вами снова Иван Протченко — инженер из команды Читать дальше

    habr.com/ru/companies/cloud_ru

    #packer #qemu #qemukvm #gitlabrunner #gitlab #gitlabci #cloudnative #qcow2 #ubuntuserver

  13. does anyone know, how many of my computer's resources can be passed to a VM? i'm on Linux (NixOS specifically)

    like let's say i want the VM to get native speed and performance, can i do that?

    #virtualization #virtualmachines #virtualisation #kvm #kernelvm #kvm #kernelbasedvirtualmachine #qemu #qemukvm #linux sorry for all the hashtags i need answers ​:BlobCat_NotLikeThisHyper:​

  14. Тестирование и отладка встраиваемых систем STM32 с использованием QEMU эмулятора и Docker

    Тестирование и отладка встраиваемых систем STM32 с использованием QEMU эмулятора и Docker На примере библиотеки логирования для STM32 с FreeRTOS мы разберем полный цикл разработки: от настройки окружения до автоматизации тестирования и отладки. Вы узнаете, как: Настроить систему автоматического тестирования STM32 проектов без реального железа Использовать Docker для создания воспроизводимой среды разработки Проводить отладку с помощью GDB и QEMU Интегрировать тесты в CI/CD pipeline Профилировать многопоточные приложения на базе FreeRTOS Описанный подход особенно актуален для команд, работающих удаленно или имеющих ограниченный доступ к тестовому оборудованию. Все примеры основаны на реальном open-source проекте и доступны на GitHub под MIT лицензией. В статье используются современные инструменты разработки: STM32CubeMX, QEMU, Docker, GDB и Visual Studio Code. Материал будет полезен как начинающим разработчикам, так и опытным инженерам, ищущим способы оптимизации процесса разработки встраиваемых систем.

    habr.com/ru/articles/865070/

    #qemu #qemukvm #docker #stm32 #github #тестирование #автоматизация #микроконтроллеры #встраиваемые_системы #системное_программирование