minseo choi · cs @ johns hopkins · mlsys researcher
I make ML models run fast.
GPU kernels · ML compilers · LLM inference systems
minseo@jhu:~$ whoami
Minseo Choi — CS @ Johns Hopkins · MLSys researcher
minseo@jhu:~$ tail -n 3 research.log
[run] JHU Medicine · six-model FP8 pipeline on 2×B200 → 2.89× decode
[run] JHU DSAI · suffix decoding → 1.43× throughput
[ok ] 119 posts · 9 projects · FlashAttention-2 from scratch
this terminal works — try
$ cat experience.log
Research Assistant · JHU Data Science & AI Institute — BLAB
Suffix decoding on a decode-bound data pipeline — 1.43× throughput
Profiled decode-bound rewriting workloads in a large-scale data-generation pipeline, found high copy-fraction, and deployed draft-free suffix decoding — 1.43× throughput with no extra training or VRAM.
suffix decoding · speculative decoding · GPU profiling
Research Assistant · Johns Hopkins Medicine — PALS Lab
Six-model FP8 safety pipeline on 2×B200 — 2.89× decode throughput
70B generator + five critic agents served with TensorRT-LLM and Triton Inference Server. Fixed orchestration-bound GPU underutilization via generator isolation, async BLS, and KV-cache block reuse — ~3,100 conversations/hour at ~3.3s P95. Now extending to heterogeneous SGLang + TensorRT-LLM serving. With NVIDIA Safety & JHTV; ICML 2027 submission planned.
TensorRT-LLM · Triton Inference Server · SGLang · FP8 · B200
Course Assistant · JHU — Computer Systems Fundamentals
Cache behavior, assembly, and performance debugging in C/C++
Drill Instructor & Senior Squad Leader · Republic of Korea Army
Trained and mentored 2,000+ recruits
$ ls projects/ --featured
flash-attention FlashAttention-2 from scratch in Triton/CUDA — ~2× faster, ~5× less peak memory vs naive attention
medical-triton Fused Triton kernels for CT/MRI pipelines — ~9.7× faster than unfused PyTorch ops
GPU-accelerated CT/MRI enhancement pipeline: DICOM preprocessing, DL denoising, and post-processing. The pre/post chains (dtype conversion, windowing, normalization, clipping) run as fused Triton kernels — ~9.7× speedup by eliminating per-op kernel launches and intermediate HBM round-trips.
kaleidoscope A small functional language, from lexer to LLVM JIT
$ tail writing.log
$ nvidia-smi --query-focus
- gpu
- CUDA · Triton · Mojo · memory hierarchy · kernel fusion
- serving
- TensorRT-LLM · vLLM · SGLang · Triton Inference Server · KV-cache reuse
- compilers
- MLIR · LLVM · TableGen · SSA/CFG · optimization passes
- infra
- C/C++ · Python · PyTorch · SLURM · Prometheus/Grafana · Linux
$ ping minseo
Looking for MLSys internships & research — GPU performance, ML compilers, or inference infrastructure. If that's your team, reach out.