Cite
Notes
Only stored in your browser.
Attribution
FlowCompile: An Optimizing Compiler for Structured LLM Workflows
arXiv 2026
CommVQ: Commutative Vector Quantization for KV Cache Compression
arXiv 2025
Steering LLM Thinking with Budget Guidance
from 3 papers
Chuang Gan
Yang Zhang
Chong Wang
Colorado Reed
Foroozan Karimzadeh
Maohao Shen
Muhammad Yusuf Hassan
Pengsheng Guo
Talha Chafekar
Tianle Cai