Skip to content
Gnosis WritingProjectsPapersAbout

The Journal

Writing

Papers and notes.

2026

Cover in preparation

贵州省高质量政府数据集建设服务评估 Aug 31

专题研究评估稿(资料截止 2026 年 8 月 6 日):围绕贵州省高质量政府数据集建设,系统评估政策依据、省级治理机制、全生命周期建设方案、风险控制与商业化路径,提出以“有效数据集”为省级绩效口径的判断尺度。

Aug 31 →

Three-Layer Progressive Optimization Aug 15

Systematic Limit Approximation for Consumer-GPU GRPO Post-Training

DGBB, ZSBR, and SFOC on one RX 7900 XTX: 795.5 tok/s (97.6% of the wall argmax), +7.8 pp from ZSBR, and 23.2% → 45.6% held-out in 8.5 hours of pure RL.

Aug 15 →

Characterizing and Optimizing LLM Post-Training Efficiency Aug 14

On Consumer AMD RDNA3 GPUs

Dual-peak MFU, gap attribution, and a tuning recipe for GRPO on a single RX 7900 XTX. Unsloth +5.2% vs HuggingFace; 4-bit −40.7%; 97.7% of the GEMM-to-GRPO gap is generation.

Aug 14 →

All rights reserved. © 2026 HongyuChen

RSS · Email · GitHub

Set in Cinzel, Barlow Condensed, Helvetica Neue & EB Garamond.

blog
  • Claude
  • ChatGPT
  • AMD
  • NVIDIA
  • OpenAIResearch
  • HuggingFace
  • GitHub
  • OpenAI
  • DeepSeek