Skip to content
Gnosis WritingProjectsPapersAbout

The Journal

Writing

Papers and notes.

2026

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.