DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with Glyd

Glyd is a Rust library and CLI that keeps bf16 model weights and KV cache in fewer bits on the GPU, restoring exact values as the model runs, and also serves as a lossless file compressor.

Trended earlier

surya-koritala/Glyd on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

4 use cases

  • Run Qwen3.5-9B on a 24 GB GPU with long context

    Fit Qwen3.5-9B on an RTX 4090 and chat in the terminal with more KV cache room.

    View prompt
    Using the repo surya-koritala/Glyd on a Linux machine with <GPU model> and driver <driver version>, install Glyd with its install script from getglyd.com and run `glyd run Qwen/Qwen3.5-9B`. Report the context length Glyd sets up and the GPU settings it applies. Verify that the terminal chat opens and returns a reply to a test question.

  • Serve Qwen3.5-9B through vLLM with Glyd quantization

    Start a vLLM server for Qwen3.5-9B using the glyd quantization option.

    View prompt
    In the repo surya-koritala/Glyd, install the vLLM extra with `pip install "glyd[vllm]"` on a machine with <GPU model>, then start `vllm serve Qwen/Qwen3.5-9B --quantization glyd`. Report the weight memory vLLM logs and compare it with the bf16 figure of 17.66 GiB in the README. Verify that a test request to the server returns a completion.

  • Load a bf16 model in Python with Glyd

    Use glyd.from_pretrained to load Qwen3.5-9B from a Python script.

    View prompt
    In the repo surya-koritala/Glyd, install the package with `pip install "glyd[vllm]"` and run `import glyd` followed by `model = glyd.from_pretrained("Qwen/Qwen3.5-9B")` on a machine with <GPU model>. Report any errors and the GPU memory in use after loading. Verify that the model object is created without an exception.

  • Compress JSON event files smaller than zstd -3

    Use the Glyd CLI to shrink a large JSON file and restore it exactly.

    View prompt
    Using the repo surya-koritala/Glyd, install the glyd CLI and compress <input file> to <output file>.glyd with `glyd --max <input file> -o <output file>.glyd`. Restore it with `glyd -d <output file>.glyd -o <restored file>`, then report both file sizes and whether the restored file matches the original. Verify that the restored file is byte-identical to the input.

How to use Glyd

  1. Check you have what it needs: Linux (x86_64 or aarch64) with an NVIDIA GPU: Ampere, Ada, Hopper or Blackwell, driver 580 or newer; For the Python and vLLM steps: Python with pip, and vLLM for serving; For the codec: Homebrew or a release tarball from the Glyd releases.
  2. Open surya-koritala/Glyd on GitHub and read the README and license.
  3. Confirm the machine runs Linux with an NVIDIA GPU (Ampere, Ada, Hopper or Blackwell) and driver 580 or newer.
  4. Review the install script at https://getglyd.com/install.sh if you do not trust the host, then run curl -LsSf https://getglyd.com/install.sh | sh.
  5. Run glyd run Qwen/Qwen3.5-9B to apply settings for your GPU and open a chat in the terminal.
  6. Send a test question and confirm a reply comes back.

These steps come from our top use case, Run Qwen3.5-9B on a 24 GB GPU with long context, which also has a copy-paste agent prompt.

Glyd alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forEngineers running open-weight models on NVIDIA GPUs who need more context or room for more requests, and developers who want a smaller lossless alternative to zstd for large JSON files.
  • Why it is hot
  • LanguageRust
  • Sourcegithub.com/surya-koritala/Glyd · Back to Hot repos

Requirements

  • Linux (x86_64 or aarch64) with an NVIDIA GPU: Ampere, Ada, Hopper or Blackwell, driver 580 or newer
  • For the Python and vLLM steps: Python with pip, and vLLM for serving
  • For the codec: Homebrew or a release tarball from the Glyd releases
  • A Glyd license from [email protected] if the work is commercial, since the README says commercial use needs one
Maintain Glyd? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/surya-koritala-glyd.svg)](https://dedupedai.com/use-cases/surya-koritala-glyd/?ref=badge)

More badge styles and HTML

Questions about Glyd

What is Glyd?

Glyd is a Rust library and CLI that keeps bf16 model weights and KV cache in fewer bits on the GPU, restoring exact values as the model runs, and also serves as a lossless file compressor. It is an open-source project on GitHub: https://github.com/surya-koritala/Glyd.

Who is Glyd for?

Engineers running open-weight models on NVIDIA GPUs who need more context or room for more requests, and developers who want a smaller lossless alternative to zstd for large JSON files.

What can I do with Glyd?

4 use cases so far, for example: Run Qwen3.5-9B on a 24 GB GPU with long context; Serve Qwen3.5-9B through vLLM with Glyd quantization; Load a bf16 model in Python with Glyd. Each has steps and a copy-paste agent prompt.

What do I need to run Glyd?

Linux (x86_64 or aarch64) with an NVIDIA GPU: Ampere, Ada, Hopper or Blackwell, driver 580 or newer; For the Python and vLLM steps: Python with pip, and vLLM for serving; For the codec: Homebrew or a release tarball from the Glyd releases; A Glyd license from [email protected] if the work is commercial, since the README says commercial use needs one.

What are alternatives to Glyd?

Other hot AI repos in Software and DevOps: Harness2, iFixAi, Orca, Diagram Design, AI Memory.

Is Glyd safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.