Skip to content
View rootonchair's full-sized avatar
❄️
❄️
55 followers · 12 following

Achievements

Achievement: Pair Extraordinairex4Achievement: StarstruckAchievement: Galaxy Brainx2Achievement: YOLOAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair Extraordinairex4Achievement: StarstruckAchievement: Galaxy Brainx2Achievement: YOLOAchievement: Pull Sharkx3Achievement: Arctic Code Vault Contributor

Block or report rootonchair

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
rootonchair/README.md

Vinh H. Pham

Open-source AI engineer in Ho Chi Minh City, working on diffusion/video generation, LLM/VLM quantization, model serving, and practical ML infrastructure.

GitHub | Hugging Face | Website

Diffusion · Video generation · LLM/VLM quantization · Model serving · Open-source ML

Open-source impact

Project ✓ Merged PRs Representative merged work
huggingface/diffusers
★ 33,746 / forks 7,011		 22 LTX2 distilled checkpoint support, framewise LTX Video VAE encoding/decoding
huggingface/transformers
★ 161,148 / forks 33,378		 8 PoolFormer fast image processor, BridgeTower fast image processor
sgl-project/sglang
★ 28,869 / forks 6,257		 1 Z-Image text encoder config fix
d2l-ai/d2l-vi
★ 659 / forks 255		 108 Vietnamese ML education translation/revision
mlbvn/ml-yearning-vi
★ 1,089 / forks 374		 23 Vietnamese ML education translation/revision
d2l-ai/d2l-en
★ 28,941 / forks 5,069		 7 Documentation fixes

Selected upstream work includes LTX2 distilled checkpoint support, LTX Video VAE framewise encoding/decoding, Diffusers pipeline/test improvements, a Z-Image fix in SGLang, and Vietnamese ML education work across Dive into Deep Learning and Machine Learning Yearning.

Adopted work

Project Integration evidence Adopting project scale
rootonchair/LTX-2-19b-distilled Listed in vLLM Omni's supported-model table for LTX2TwoStagesPipeline and LTX2ImageToVideoTwoStagesPipeline ★ 4,858 / forks 1,028
rootonchair/diffuser_layerdiffuse SD.Next includes a LayerDiffuse: Transparent Image extension and links back to this project in the extension UI ★ 7,113 / forks 558

Selected AI systems work

  • Video: Diffusers integrations, LTX video support, transparent image generation, and model execution workflows.
  • Quantization: GGUF and AWQ releases for image-text models such as Vintern-3B, Vintern-1B, EraX-VL-7B, and InternVL2.5-4B.
  • Serving: quantized/GGUF model artifacts, runtime tooling, and diffusion model compression experiments.
  • Tooling: practical patches across Hugging Face Diffusers/Transformers and related open-source ML projects.

Current focus

I am mostly interested in making generative models easier to run, adapt, compress, and serve in real systems.

Pinned Loading

  1. huggingface/diffusers huggingface/diffusers Public

    🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

    Python 33.8k 7k

  2. huggingface/transformers huggingface/transformers Public

    🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

    Python 161k 33.4k

  3. d2l-ai/d2l-en d2l-ai/d2l-en Public

    Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

    Python 29k 5.1k

  4. diffuser_layerdiffuse diffuser_layerdiffuse Public

    Create transparent image with Diffusers!

    Python 61 3