Refined LiteRTLM scheduling plots and log parsing — 1.1M tokens

@ishang97· Jun 9

Refined LiteRTLM scheduling plots and log parsing

litertlm_s26_ultra_sched_freq_7_jun_2026

FULL SEND

9.0x your typical session

1.1M tokens vs typical 123.1K

1.1Mtokens

14prompts

3:15:59time

1,924lines

Codexgpt-5.5Python$11.90

Adjusted LiteRTLM S26 Ultra scheduling experiment scripts, log-to-CSV conversion, and decode-rate plotting across related variants, with tests added for the plotting and log parsing paths.

Tokens / prompt79.4k

Cost / line$0.006

Cache hit90%

Burn rate$3.64/hr

Derived from this session's token and cost data. Not shown on the feed.

Building now

Top builders this week

9.0x your typical session

Comments