Park Soobin

subin

·

https://cv.subin.rs

AI & ML interests

LLM inference and serving — vLLM internals, chat templates, tokenization, and NPU/GPU deployment.

Recent Activity

liked a Space 3 days ago

multimodalart/jev-decision-index

new activity 4 days ago

vllm-sr/d3:Quantized version for vLLM support

upvoted a collection 4 days ago

Decision models

View all activity

Organizations

New activity in vllm-sr/d3 4 days ago

Quantized version for vLLM support

#2 opened 4 days ago by

New activity in vllm-sr/d3-flash 5 days ago

how to deploy the model?

#1 opened 5 days ago by

New activity in vllm-sr/Decision-1.0-Route-0.6B 16 days ago

Update the fine-tuned weights

#2 opened 16 days ago by

New activity in vllm-sr/Decision-1.0-Lux-9B 16 days ago

Make the hardware wording neutral

#1 opened 16 days ago by

New activity in vllm-sr/Decision-1.0-Nox-4B 16 days ago

Make the hardware wording neutral

#1 opened 16 days ago by

New activity in vllm-sr/Decision-1.0-Sol-2B 16 days ago

Make the hardware wording neutral

#1 opened 16 days ago by

New activity in vllm-sr/Decision-1.0-Eos-0.8B 16 days ago

Make the hardware wording neutral

#2 opened 16 days ago by

New activity in vllm-sr/Decision-1.0-Route-0.6B 18 days ago

Add the router-signal fine-tune of Decision-1.0-Kai-0.6B

#1 opened 18 days ago by

New activity in LGAI-EXAONE/EXAONE-4.0-32B 2 months ago

Guard tool_call arguments against pre-serialized JSON strings (align with EXAONE 4.5)

#14 opened 2 months ago by