TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control
"NVFP4" 相关文章
QeRL: NVFP4-Quantized Reinforcement Learning (RL) Brings 32B LLM Training to a Single H100—While Improving Exploration
NVIDIA Blackwell Leads on SemiAnalysis InferenceMAX™ v1 Benchmarks
NVIDIA Blackwell Ultra Sets the Bar in New MLPerf Inference Benchmark
NVIDIA Rubin CPX Accelerates Inference Performance and Efficiency for 1M+ Token Context Workloads
NVIDIA Blackwell Ultra Sets New Inference Records in MLPerf Debut
How Quantization Aware Training Enables Low-Precision Accuracy Recovery
Optimizing LLMs for Performance and Accuracy with Post-Training Quantization
Inside NVIDIA Blackwell Ultra: The Chip Powering the AI Factory Era
NVFP4 Trains with Precision of 16-Bit and Speed and Efficiency of 4-Bit
Fine-Tuning gpt-oss for Accuracy and Performance with Quantization Aware Training
与国产AI分裂 NVIDIA最强AI显卡GB300强化FP4：能效暴增50倍
与国产AI分裂 NVIDIA最强AI显卡GB300强化FP4：能效暴增50倍
