Pinned Repositories
EnvPipe
HUVM
jos
pintos-kaist
flash-attention
Fast and memory-efficient exact attention
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
sjchoi1.github.io
A Theme for GitHub Pages
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
xilinx_xdma_driver
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
sjchoi1's Repositories
sjchoi1/xilinx_xdma_driver
sjchoi1/flash-attention
Fast and memory-efficient exact attention
sjchoi1/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
sjchoi1/sjchoi1.github.io
A Theme for GitHub Pages
sjchoi1/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs