Informal's blog

Wander around

HOME
TAGS
ARCHIVES
TREASURE
ABOUT

Home Tags GRPO

Tag

GRPO 1

GRPO May 20, 2025

Recently Updated

LLM Post-Training experience
Better idea between Copilot-typed and CLI-typed assistant
Outline of LLM acceleration
AutoSwitch Translate
Cross Entropy Loss of Triton

Trending Tags

Weekly LLM acceleration fine-tune attention Claude-code code-assistant Copilot find-tune flash-attention

© 2025 Informal. Some rights reserved.

Using the Chirpy theme for Jekyll.

Trending Tags

Weekly LLM acceleration fine-tune attention Claude-code code-assistant Copilot find-tune flash-attention

A new version of content is available.