home.social

#memoryusage — Public Fediverse posts

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

  1. How to significantly reduce memory usage of GTK4 applications in computers with low RAM running Ubuntu? #ram #memoryusage #gtk4

    askubuntu.com/q/1566199/612

  2. How to significantly reduce memory usage of GTK4 applications in computers with low RAM running Ubuntu? #ram #memoryusage #gtk4

    askubuntu.com/q/1566199/612

  3. How to significantly reduce memory usage of GTK4 applications in computers with low RAM running Ubuntu? #ram #memoryusage #gtk4

    askubuntu.com/q/1566199/612

  4. How to significantly reduce memory usage of GTK4 applications in computers with low RAM running Ubuntu? #ram #memoryusage #gtk4

    askubuntu.com/q/1566199/612

  5. How to significantly reduce memory usage of GTK4 applications in computers with low RAM running Ubuntu? #ram #memoryusage #gtk4

    askubuntu.com/q/1566199/612

  6. Ars Technica: Google’s TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x. “Google Research recently revealed TurboQuant, a compression algorithm that reduces the memory footprint of large language models (LLMs) while also boosting speed and maintaining accuracy.”

    https://rbfirehose.com/2026/03/26/ars-technica-googles-turboquant-ai-compression-algorithm-can-reduce-llm-memory-usage-by-6x/
  7. Ars Technica: Google’s TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x. “Google Research recently revealed TurboQuant, a compression algorithm that reduces the memory footprint of large language models (LLMs) while also boosting speed and maintaining accuracy.”

    https://rbfirehose.com/2026/03/26/ars-technica-googles-turboquant-ai-compression-algorithm-can-reduce-llm-memory-usage-by-6x/
  8. Ars Technica: Google’s TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x. “Google Research recently revealed TurboQuant, a compression algorithm that reduces the memory footprint of large language models (LLMs) while also boosting speed and maintaining accuracy.”

    https://rbfirehose.com/2026/03/26/ars-technica-googles-turboquant-ai-compression-algorithm-can-reduce-llm-memory-usage-by-6x/
  9. Ars Technica: Google’s TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x. “Google Research recently revealed TurboQuant, a compression algorithm that reduces the memory footprint of large language models (LLMs) while also boosting speed and maintaining accuracy.”

    https://rbfirehose.com/2026/03/26/ars-technica-googles-turboquant-ai-compression-algorithm-can-reduce-llm-memory-usage-by-6x/
  10. Ars Technica: Google’s TurboQuant AI-compression algorithm can reduce LLM memory usage by 6x. “Google Research recently revealed TurboQuant, a compression algorithm that reduces the memory footprint of large language models (LLMs) while also boosting speed and maintaining accuracy.”

    https://rbfirehose.com/2026/03/26/ars-technica-googles-turboquant-ai-compression-algorithm-can-reduce-llm-memory-usage-by-6x/
  11. === KIỂM TRA NHANH SỬ DỤNG RAM TRÊN LINUX ===

    📊 Tổng quan: Tổng, đã dùng, trống, khả dụng
    🔝 10 tiến trình tốn RAM nhất
    🗂 Phân loại: Ứng dụng vs hệ thống (kernel, cache)
    💡 Mẹo: Dọn cache nếu cần (sudo sync && echo 3 > /proc/sys/vm/drop_caches)

    Script hoạt động trên mọi hệ thống Linux, hiển thị rõ bộ nhớ thực và khả dụng. Cache nằm trong "available" là bình thường.

    #Linux #Bash #RAM #MemoryUsage #Scripting #LinuxTips
    #Linux #Bash #RAM #Sử_dụng_bộ_nhớ #ShellScript #Mẹo_Linux

    h

  12. #Huawei’s Computing Systems Lab introduced #SINQ, an #opensource #quantisationmethod for large language models (#LLMs). SINQ reduces #memoryusage by 60-70% without sacrificing output quality, enabling models to run on less powerful #hardware. The technique, available on GitHub and Hugging Face, uses #dualaxisscaling and #SinkhornKnopp-style #normalisation for improved performance. venturebeat.com/ai/huaweis-new #tech #media #news

  13. #Huawei’s Computing Systems Lab introduced #SINQ, an #opensource #quantisationmethod for large language models (#LLMs). SINQ reduces #memoryusage by 60-70% without sacrificing output quality, enabling models to run on less powerful #hardware. The technique, available on GitHub and Hugging Face, uses #dualaxisscaling and #SinkhornKnopp-style #normalisation for improved performance. venturebeat.com/ai/huaweis-new #tech #media #news

  14. #Huawei’s Computing Systems Lab introduced #SINQ, an #opensource #quantisationmethod for large language models (#LLMs). SINQ reduces #memoryusage by 60-70% without sacrificing output quality, enabling models to run on less powerful #hardware. The technique, available on GitHub and Hugging Face, uses #dualaxisscaling and #SinkhornKnopp-style #normalisation for improved performance. venturebeat.com/ai/huaweis-new #tech #media #news

  15. #Huawei’s Computing Systems Lab introduced #SINQ, an #opensource #quantisationmethod for large language models (#LLMs). SINQ reduces #memoryusage by 60-70% without sacrificing output quality, enabling models to run on less powerful #hardware. The technique, available on GitHub and Hugging Face, uses #dualaxisscaling and #SinkhornKnopp-style #normalisation for improved performance. venturebeat.com/ai/huaweis-new #tech #media #news

  16. #Huawei’s Computing Systems Lab introduced #SINQ, an #opensource #quantisationmethod for large language models (#LLMs). SINQ reduces #memoryusage by 60-70% without sacrificing output quality, enabling models to run on less powerful #hardware. The technique, available on GitHub and Hugging Face, uses #dualaxisscaling and #SinkhornKnopp-style #normalisation for improved performance. venturebeat.com/ai/huaweis-new #tech #media #news

  17. I’m working on a project that has some memory issues with their jobs.

    Used a memory profiler, one job made just over 1,000,000,000 memory allocations (billion, with a b!)

    I’ve my work cut out, but I think I’m gonna learn a tonne about memory best practice

    #RubyOnRails #Performance #MemoryUsage

  18. The sad state of the web browsers is that I have open more than 200 tabs, but because I use "UnloadTabs" extensions, only a handful is actively loaded. If all those tabs would be activated all of my 8 GB RAM would disappera in 5 seconds, machine locked up and dead. And yes, while I don't need all of them, it's good to have them at my fingertips.

    I think, I will look for an extension similar to what Edge have in "Collections", basically bookmarked tabs, but in a separate way with descriptions and shit. Pretty good idea, and I like how Edge devs made something that stands out from the usual browser stuff.

    #web #browser #memoryusage
  19. I’m working on a project that has some memory issues with their jobs.

    Used a memory profiler, one job made just over 1,000,000,000 memory allocations (billion, with a b!)

    I’ve my work cut out, but I think I’m gonna learn a tonne about memory best practice

    #RubyOnRails #Performance #MemoryUsage

  20. I’m working on a project that has some memory issues with their jobs.

    Used a memory profiler, one job made just over 1,000,000,000 memory allocations (billion, with a b!)

    I’ve my work cut out, but I think I’m gonna learn a tonne about memory best practice

    #RubyOnRails #Performance #MemoryUsage

  21. I’m working on a project that has some memory issues with their jobs.

    Used a memory profiler, one job made just over 1,000,000,000 memory allocations (billion, with a b!)

    I’ve my work cut out, but I think I’m gonna learn a tonne about memory best practice

    #RubyOnRails #Performance #MemoryUsage

  22. I’m working on a project that has some memory issues with their jobs.

    Used a memory profiler, one job made just over 1,000,000,000 memory allocations (billion, with a b!)

    I’ve my work cut out, but I think I’m gonna learn a tonne about memory best practice

    #RubyOnRails #Performance #MemoryUsage

  23. Google Chrome has a new feature that tells you exactly how much memory the websites you visit are using up. Why's this so great? It stops your PC or laptop from unexpectedly slowing down. Woo hoo!

    #GoogleChrome #MemoryUsage #NewFeature digitaltrends.com/computing/go