Skip to content
View cattermelon1234's full-sized avatar

Highlights

  • Pro

Block or report cattermelon1234

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
cattermelon1234/README.md

hi, i'm brian 👋

i study cs @ penn. interested in ml, inference, ULL systems

Pinned Loading

  1. relaxed-recursive-transformer relaxed-recursive-transformer Public

    pytorch implementation of relaxed recursive transformer architecture with layer-wise LoRA

    Python 1

  2. cactus-compute/engine cactus-compute/engine Public

    2bit quants, kernels and runtime for consumer devices.

    C++ 6.2k 516

  3. kernels kernels Public

    implementation of various gpu kernels from scratch

    Cuda

  4. qwen qwen Public

    qwen3 implementation from scratch

    Python

  5. micro-vllm micro-vllm Public

    inference engine based on the vLLM system. WIP :)

    Python

  6. dpdk-kv-store dpdk-kv-store Public

    single node kv storage utilizing dpdk

    C++