Quartet: Native FP4 Training Can Be Optimal for Large Language Models
Paper
• 2505.14669 • Published
• 78
Kyle Sayers
kylesayrs
AI & ML interests
Accelerating ML inference @ Red Hat
Recent Activity
updated
a model 7 days ago
nm-testing/tinyllama-w8a16-dense updated
a model 8 days ago
inference-optimization/Kimi-K2-Instruct-0905-BF16-FP8-BLOCK published
a model 8 days ago
inference-optimization/Kimi-K2-Instruct-0905-BF16-FP8-BLOCK Organizations
