Skip to content
View uuirs's full-sized avatar

Block or report uuirs

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. 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
uuirs/README.md

long chen / uuirs

ML systems engineer focused on JAX, model inference, and on-device AI.

I work on practical inference systems across JAX, PyTorch, CoreML, ONNX, WebGPU, and Swift. My current focus is lightweight video segmentation/tracking, edge deployment, and long-sequence streaming models.

Selected open-source contributions

JAX

  • jax-ml/jax #27292 — Fix wrong unpacking in the decode attention Pallas kernel
    Merged. Fixed an output-structure mismatch in the decode attention Pallas kernel that could cause shape mismatches and incorrect assertions when batch_size > 1.

Equinox

  • patrick-kidger/equinox #235 — Support buffer donation in filter_jit
    Merged. Added support for controlling JAX buffer donation through donate_default, donate_args, donate_kwargs, and donate_fn.

  • patrick-kidger/equinox #233 — Fix tree_inference
    Merged. Fixed repeated node collection in nested PyTrees, reducing unnecessary traversal work in deeply nested module structures.

  • patrick-kidger/equinox #190 — Fix attention mask handling and add tests
    Merged. Fixed mask axis handling in attention and added regression tests.

Current work

Edge video tracking / segmentation

Building lightweight video object tracking and segmentation pipelines for mobile and browser deployment.

Areas involved:

  • EdgeTAM / SAM2-style video tracking
  • CoreML model splitting and quantization
  • Swift native inference
  • ONNX / WebGPU deployment
  • Mask generation for interactive visual effects

Technical focus

  • JAX / PyTorch / Equinox
  • Pallas kernels and inference correctness
  • CoreML / ONNX / WebGPU
  • Swift / iOS native inference
  • Long-sequence and streaming model systems
  • Edge AI product prototyping

I prefer building small, verifiable systems: model export, numerical comparison, runtime integration, and deployment on constrained devices.

Popular repositories Loading

  1. lightweight-gan lightweight-gan Public

    Forked from lucidrains/lightweight-gan

    Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two

    Python

  2. dotfiles dotfiles Public

    Forked from thoughtbot/dotfiles

    A set of vim, zsh, git, and tmux configuration files.

    Shell

  3. jax jax Public

    Forked from jax-ml/jax

    Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

    Python

  4. equinox equinox Public

    Forked from patrick-kidger/equinox

    Callable PyTrees and filtered transforms => neural networks in JAX. https://docs.kidger.site/equinox/

    Python

  5. flax flax Public

    Forked from google/flax

    Flax is a neural network library for JAX that is designed for flexibility.

    Python

  6. diffusers diffusers Public

    Forked from huggingface/diffusers

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

    Python