Edition of Sunday 15 November 2026

microsoft/onnxruntime plugin-ep-cuda/v0.4.0

Comments on “microsoft/onnxruntime plugin-ep-cuda/v0.4.0”

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

The microsoft/onnxruntime plugin-ep-cuda v0.4.0 release, published by Microsoft's ONNX Runtime project, adds CPU/GPU hybrid expert offloading for Mixture-of-Experts models that exceed GPU memory, plus new quantized MoE kernels (INT2/INT3/INT4, offline NVFP4) and long-context and speculative-decoding speedups.

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. 54 of 62 with a score of 0.62. The panel rated it highest on technical depth (0.93) and new information (0.93), lowest on audience breadth (0.43). Placed No. 54, No. 27 by score alone: the 27th AI & machine learning story of the day (−0.080), and close to “microsoft/onnxruntime v1.32.0”, No. 22 on Saturday 14 November 2026 (−0.050). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Detailed technical release notes for a major ML inference runtime's CUDA plugin, with specifics on kernels and options; useful to ML infra builders but niche in audience and largely a changelog.
AI judgeJudge 3gpt-5.6-luna
A highly technical CUDA/ONNX Runtime release with substantial new quantization, MoE offloading, attention, speculative decoding, compatibility, and packaging details. It is actionable for AI inference builders, though specialized and release-note formatted.

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

0.62total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.60
  • Reader interest0.59
  • Audience breadth0.43
  • Practical relevance0.74
  • Substantiated0.78
  • Technical depth0.93
  • New information0.93
  • Counts against: Promotional0.09
  • Counts against: Overclaim0.14

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?0.670.400.720.600.32+0.24+0.143
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.590.400.780.590.38+0.26+0.153
Audience breadthHow many people who build technology does it concern?0.410.300.580.430.28+0.13+0.056
Practical relevanceHow useful is it to someone who builds software or tech products?0.810.600.820.740.22+0.22+0.164
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.0.820.600.910.780.31+0.05+0.039
Technical depthHow technically substantive is it?0.970.850.980.930.13+0.05+0.047
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.920.900.960.930.06+0.05+0.046
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.0.070.150.040.090.11−0.19−0.016
OverclaimDo the headline or conclusions claim more than the body supports?0.180.200.050.140.15−0.11−0.016
Sum of contributions+0.616
Claim-check penalty0.000
Total, as published0.616

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 #54 on Rubric, 15 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-15/54/"><img src="https://rubric.hrih.si/badge/2026-11-15/54.svg" alt="Ranked #54 on Rubric, 15 Nov 2026" width="245" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN —

Recorded for context only, checked 15 Nov 2026, 20:46 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 “microsoft/onnxruntime plugin-ep-cuda/v0.4.0”

More on Rubric

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

  1. Score 0.75

    llama.cpp v1.0