Park Soobin
AI & ML interests
LLM inference and serving — vLLM internals, chat templates, tokenization, and NPU/GPU deployment.
Recent Activity
new activity 1 day ago
vllm-sr/d3-ultra:Card: state 26B to match the parameter count, add the release date new activity 2 days ago
vllm-sr/d3-turbo-NVFP4:Pass the runtime's states through split_on_oom (TypeError on warmup) new activity 2 days ago
vllm-sr/d3-ultra-NVFP4:Pass the runtime's states through split_on_oom (TypeError on warmup)