Arun Kumar
narotra05hp
·
AI & ML interests
Transformer inference and attention variants. I write primary-source explainers at diffstudy.com — reading the papers and checking what they actually measured.
Recent Activity
new activity 15 days ago
Qwen/Qwen2.5-Coder-32B-Instruct:How to run speculative decoding of this model with 0.5B model. new activity 18 days ago
deepseek-ai/DeepSeek-R1:Draft model as accelerator for DeepSeek-R1?Organizations
None yet