About

Welcome

BitDance: Computing NVFP4 on MXFP6 Hardware

MXFP and NVFP: Block Scales, Two-Level Scaling, and Quantization Error

AMD 2027 Spring Research Internships

Welcome to the English edition of YIN Xuanwu's technical blog.

Folding NVFP4 B32 E4M3 scales into MXFP6 to preserve 4-bit weight storage while using native MXFP6 compute, with weight, operator, end-to-end, memory, and performance results.

A comparison of MXFP4, MXFP6, and NVFP4, focusing on block-scale formats, two-level scaling, and weight-only quantization error.

技术分享

Hiring

AMD 2027 Spring Research Internship opportunities.

中文

Switch to the explicit Chinese locale route so browser language preferences cannot redirect back to English.

LLM Quantization

公告

SEO Difficulty Score

External Mentions

Related Notion Pages

Content Freshness Tier

password

icon

date

type

CAN_COPY

slug

status

title

summary

Config

Post Board

Table

Post Gallery

Research internships in Speculative Decoding, On-Policy Distillation, and Low-Precision Training for Master's or Ph.D. students graduating in 2029 or later.

1. Research Intern - LLM Speculative Decoding

2. Research Intern - On-Policy Distillation

3. Research Intern - Low-Precision Training

Technology, Practice, and Reflections by YIN Xuanwu

社区

社区