ICML

Showing 1 of 15 posts tagged ICML

All15 Alignment Autoresearch ICML Image Generation Mechanistic Interpretability Multi-Agent Systems Pre-Training RL SFT Sparse Autoencoders Trustworthy AI

[ICML ’26 Effort] Efficient Qwen: Making Qwen3.5-4B Faster on a Single A10G

My ICML 2026 AdaptFM effort to optimize Qwen3.5-4B for low-latency inference on a single NVIDIA A10G through 100+ runtime, compiler, and quantization experiments.

June 30, 2026

June 30, 2026reads

[ICML ’26 Effort] Efficient Qwen: Making Qwen3.5-4B Faster on a Single A10G

My ICML 2026 AdaptFM effort to optimize Qwen3.5-4B for low-latency inference on a single NVIDIA A10G through 100+ runtime, compiler, and quantization experiments.