Demystifying Numerical Instability in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL
cs.LG
Submitted: 2026-06-19
Updated: 2026-11-08
Code: https://github.com/vllm-project/vllm
Terminology
Sources
- Automatic Evaluation of Healthcare LLMs Beyond Question-Answering
- LLM-42: Enabling Determinism in LLM Inference with Verified Speculation
- The Llama 3 Herd of Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams
- Defeating the Training-Inference Mismatch via FP16
- The Anatomy of a Triton Attention Kernel
- Massive Activations in Large Language Models
- Qwen3 Technical Report
- Deterministic Inference across Tensor Parallel Sizes That Eliminates Training-Inference Mismatch
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis