Edition of Friday 20 November 2026

I built a tool that finds the fastest way to serve an LLM on your GPU

Comments on “I built a tool that finds the fastest way to serve an LLM on your GPU”

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

rigtune is an open-source tool that benchmarks serving engines (vLLM, SGLang, llama.cpp), weight precisions, KV-cache types and speculative decoding on a user's own GPU and prompts, then serves the fastest configuration via an OpenAI-compatible API.

Read the original at github.com. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Why it ranked

No. 66 of 140 with a score of 0.61. The panel rated it highest on new information (0.91) and technical depth (0.90), lowest on audience breadth (0.48). Placed No. 66, No. 56 by score alone: the 16th AI & machine learning story of the day (−0.080). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Open-source tool with detailed, mostly self-caveated benchmarks on LLM serving; practical for builders, limited to two models and Ampere GPUs, measurements self-reported and not independently replicated.
AI judgeJudge 3gpt-5.6-luna
A technically detailed, reproducible benchmarking and serving tool with useful GPU/model/workload comparisons. Its evidence is unusually candid, but scope is limited and the headline generalizes beyond the tested hardware, models, and traffic.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.61total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.50
  • Reader interest0.74
  • Audience breadth0.48
  • Practical relevance0.81
  • Substantiated0.82
  • Technical depth0.90
  • New information0.91
  • Counts against: Promotional0.15
  • Counts against: Overclaim0.38

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.540.350.620.500.27+0.24+0.121
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.730.600.880.740.28+0.26+0.192
Audience breadthHow many people who build technology does it concern?0.470.400.580.480.18+0.13+0.063
Practical relevanceHow useful is it to someone who builds software or tech products?0.870.700.860.810.17+0.22+0.178
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.970.600.880.820.37+0.05+0.041
Technical depthHow technically substantive is it?0.990.800.910.900.19+0.05+0.045
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.890.900.930.910.04+0.05+0.045
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.070.300.080.150.23−0.19−0.028
OverclaimDo the headline or conclusions claim more than the body supports?0.450.350.340.380.11−0.11−0.042
Sum of contributions+0.614
Claim-check penalty0.000
Total, as published0.614

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #66 on Rubric, 20 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-20/66/"><img src="https://rubric.hrih.si/badge/2026-11-20/66.svg" alt="Ranked #66 on Rubric, 20 Nov 2026" width="245" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 1 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 20 Nov 2026, 05:47 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “I built a tool that finds the fastest way to serve an LLM on your GPU”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.