9 papers · 1 filter
miniTE: Diagnosing and Bridging the Execution Gap in Native NVFP4 Reinforcement Learning
Zhen Li, Mingfa Feng, Yiming Zhang +6
Native NVFP4 promises to accelerate reinforcement learning (RL) for large language models (LLMs), but achieving stable learning across separate training and sampling engines remain…
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
Changhai Zhou, Kieran Liu, Yuhua Zhou +17
Long-context RL post-training is constrained by the lifetime of state and gradients, not attention cost alone. In GRPO, one multi-million-token prompt must serve old-policy and ref…
BUDDY: BUdget-Driven DYnamic Depth Routing for Adaptive Large Language Model Inference
Yuhua Zhou, Shaoqi Yu, Shichao Weng +4
Large language models (LLMs) incur high inference cost due to their depth and parameter scale. Depth pruning can reduce latency by skipping redundant Transformer blocks, but existi…
MinT: Managed Infrastructure for Training and Serving Millions of LLMs
Mind Lab, :, Song Cao +60
We present MindLab Toolkit (MinT), a managed infrastructure system for Low-Rank Adaptation (LoRA) post-training and online serving. MinT targets a setting where many trained polici…
AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning
Changhai Zhou, Shiyang Zhang, Yuhua Zhou +5
Quantization followed by parameter-efficient fine-tuning has emerged as a promising paradigm for downstream adaptation under tight GPU memory constraints. However, this sequential…
Balancing Fidelity and Plasticity: Aligning Mixed-Precision Fine-Tuning with Linguistic Hierarchies
Changhai Zhou, Shiyang Zhang, Yuhua Zhou +5
Deploying and fine-tuning Large Language Models (LLMs) on resource-constrained edge devices requires navigating a strict trade-off between memory footprint and task performance. Wh…
Large Language Model Compression with Global Rank and Sparsity Optimization
Changhai Zhou, Qian Qiao, Yuhua Zhou +4
Low-rank and sparse composite approximation is a natural idea to compress Large Language Models (LLMs). However, such an idea faces two primary challenges that adversely affect the…
QPruner: Probabilistic Decision Quantization for Structured Pruning in Large Language Models
Changhai Zhou, Yuhua Zhou, Shijie Han +2
The rise of large language models (LLMs) has significantly advanced various natural language processing (NLP) tasks. However, the resource demands of these models pose substantial…
AutoMixQ: Self-Adjusting Quantization for High Performance Memory-Efficient Fine-Tuning
Changhai Zhou, Shiyang Zhang, Yuhua Zhou +2
Fine-tuning large language models (LLMs) under resource constraints is a significant challenge in deep learning. Low-Rank Adaptation (LoRA), pruning, and quantization are all effec…