|

• info
• AI engineer
• github repo
• LinkedIn
• LLM inference & ML systems
• contributing to vLLM (& llm-compressor), SGLang, ONNX Runtime — so far on quantization, SD, attention kernels (my PRs)
• Pinned Posts
• 2026-04-21 torch.compile 탐구생활
• 2025-12-02 Int4 to FP16 dequantization optimization
• 2024-09-27 Matryoshka Representation Learning Review
• all posts
• 2026-04-21 torch.compile 탐구생활
• 2026-02-07 FFT on GPU
• 2025-12-28 Data_format
• 2025-12-02 Int4 to FP16 dequantization optimization
• See all...
• categories
• algorithm
• optimization
• NLP
• Machine Learning
• ...
• 공사중...
• 공사중...
• 공사중...
• 공사중...
• 공사장의 구석..
• TIP
• Working....