Pinned Repositories
blog_examples
cccl
CUDA C++ Core Libraries
cupy
NumPy & SciPy for GPU
cutlass
CUDA Templates for Linear Algebra Subroutines
gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
kubernetes
Production-Grade Container Scheduling and Management
milesvant.github.io
mp4-to-txt
Transcribe videos stored in filesystem
nvim.config
ray
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
milesvant's Repositories
milesvant/nvim.config
milesvant/mp4-to-txt
Transcribe videos stored in filesystem
milesvant/blog_examples
milesvant/cccl
CUDA C++ Core Libraries
milesvant/cupy
NumPy & SciPy for GPU
milesvant/cutlass
CUDA Templates for Linear Algebra Subroutines
milesvant/gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
milesvant/kubernetes
Production-Grade Container Scheduling and Management
milesvant/milesvant.github.io
milesvant/ray
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
milesvant/scipy
SciPy library main repository
milesvant/triton
Development repository for the Triton language and compiler
milesvant/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs