Quartet: Native FP4 Training Can Be Optimal for Large Language Models
Paper
• 2505.14669 • Published
• 78
Brian Dellabetta
bdellabe
AI & ML interests
None yet
Recent Activity
updated
a model about 14 hours ago
bdellabe/DeepSeek-V3.2-NVFP4-FP8-BLOCK published
a model about 14 hours ago
bdellabe/DeepSeek-V3.2-NVFP4-FP8-BLOCK updated
a model about 14 hours ago
bdellabe/DeepSeek-R1-NVFP4-FP8-BLOCK Organizations
upvoted a paper 10 months ago