Edition of Saturday 14 November 2026

microsoft/onnxruntime v1.32.0

Comments on “microsoft/onnxruntime v1.32.0”

Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked

ONNX Runtime 1.32.0 is a release that upgrades ONNX to 1.23.2 with opset 28 operator support, adds a CPU/GPU hybrid offload path for quantized Mixture-of-Experts models, and expands device-memory and weightless-compilation APIs. It also cuts session initialization on very large, constant-heavy graphs from minutes to seconds.

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. 22 of 123 with a score of 0.69. The panel rated it highest on new information (0.93) and technical depth (0.89), lowest on audience breadth (0.58). Placed No. 22, No. 11 by score alone: the seventh 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
Major release of a widely used ML inference runtime with substantial feature and performance changes; detailed changelog but mostly a list of changes with limited independent evidence, and breaking API removals noted.
AI judgeJudge 3gpt-5.6-luna
A primary, highly technical release with substantial ONNX, quantization, MoE, execution-provider, API, performance, and reliability changes. It is actionable for inference and ML infrastructure builders, though its breadth limits significance beyond those communities.

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

0.69total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.67
  • Reader interest0.70
  • Audience breadth0.58
  • Practical relevance0.78
  • Substantiated0.81
  • Technical depth0.89
  • New information0.93
  • Counts against: Promotional0.08
  • Counts against: Overclaim0.17

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?0.730.550.720.670.18+0.24+0.160
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.670.600.830.700.23+0.26+0.182
Audience breadthHow many people who build technology does it concern?0.570.550.620.580.07+0.13+0.075
Practical relevanceHow useful is it to someone who builds software or tech products?0.870.700.780.780.17+0.22+0.173
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.0.910.600.910.810.31+0.05+0.040
Technical depthHow technically substantive is it?0.960.800.900.890.16+0.05+0.044
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.920.900.980.930.08+0.05+0.047
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.0.050.100.080.080.05−0.19−0.015
OverclaimDo the headline or conclusions claim more than the body supports?0.190.200.120.170.08−0.11−0.019
Sum of contributions+0.688
Claim-check penalty0.000
Total, as published0.688

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 #22 on Rubric, 14 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-14/22/"><img src="https://rubric.hrih.si/badge/2026-11-14/22.svg" alt="Ranked #22 on Rubric, 14 Nov 2026" width="245" height="28"></a>

Claim check

Claim check: 1 no source given · 7 couldn’t check. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.

  1. Couldn’t checkVersion

    ONNX Runtime 1.32.0 reintegrates ONNX 1.23.2 with opset 28 operator support (SpaceToDepth, Mod, signed BitShift, BFloat16 extensions) and updates DLPack to v1.3.

    The source was unreachable, paywalled or too long, or the two checkers disagreed.

    The article says

    “Reintegrated ONNX 1.23.2 with opset 28 operator support (SpaceToDepth, Mod, signed BitShift, and BFloat16 extensions) and updated DLPack to v1.3”

    The source says

    No passage could be compared.

    Source cited by the article: github.com/microsoft/onnxruntime/pull/33134

  2. Couldn’t checkNumber

    Session creation time on 100k-node constant-heavy graphs dropped from over 10 minutes to about 5 seconds after removing superlinear scans in the allocation planner and related passes.

    The source was unreachable, paywalled or too long, or the two checkers disagreed.

    The article says

    “cutting session creation time on 100k-node constant-heavy graphs from over 10 minutes to ~5 seconds”

    The source says

    No passage could be compared.

    Source cited by the article: github.com/microsoft/onnxruntime/pull/33407

  3. Couldn’t checkVersion

    ONNX Runtime 1.32.0 added a session-scoped CPU/GPU hybrid MoE offload planner and execution backend for quantized QMoE (NVFP4, INT4, INT3, INT2) and MoEPacked models.

    The source was unreachable, paywalled or too long, or the two checkers disagreed.

    The article says

    “Added a session-scoped CPU/GPU hybrid MoE offload planner and execution backend for quantized QMoE (NVFP4, INT4, INT3, and INT2) and block-packed MoEPacked models”

    The source says

    No passage could be compared.

    Source cited by the article: github.com/microsoft/onnxruntime/pull/33450

  4. Couldn’t checkVersion

    The ACL execution provider (ACLExecutionProvider), its build options and its C registration API were removed in 1.32.0 after deprecation in 1.31.0.

    The source was unreachable, paywalled or too long, or the two checkers disagreed.

    The article says

    “ACL EP removed: Following its deprecation in 1.31.0, the Arm Compute Library (ACLExecutionProvider) execution provider, its build options, and its standalone C registration API have been removed”

    The source says

    No passage could be compared.

    Source cited by the article: github.com/microsoft/onnxruntime/pull/33851

  5. Couldn’t checkVersion

    CUDA Plugin EP v0.4.0 and WebGPU Plugin EP v0.6.0 are matched with ONNX Runtime 1.32.0.

    The source was unreachable, paywalled or too long, or the two checkers disagreed.

    The article says

    “CUDA Plugin EP v0.4.0 and WebGPU Plugin EP v0.6.0 are matched with ONNX Runtime 1.32.0”

    The source says

    No passage could be compared.

    Source cited by the article: github.com/microsoft/onnxruntime/pull/33214

  6. Couldn’t checkVersion

    DLPack v1.3 support covers all implemented ORT numeric and boolean types including five float8 formats, packed float4, int4/uint4 and int2/uint2, while float6 remains unsupported.

    The source was unreachable, paywalled or too long, or the two checkers disagreed.

    The article says

    “bidirectional support for all implemented ORT numeric and boolean types, including all five float8 formats, packed float4, int4/uint4, and int2/uint2 (float6 remains unsupported in DLPack”

    The source says

    No passage could be compared.

    Source cited by the article: github.com/microsoft/onnxruntime/pull/33848

  7. No source givenNumber

    Switching the Linux aarch64 wheel to Blackwell family targets (100f, 120f) saves about 82 MB.

    The article gives no link or citation for it.

    The article says

    “switched the Linux aarch64 wheel to Blackwell family targets (100f, 120f, saving ~82 MB”

    The source says

    No source to compare with.

  8. Couldn’t checkVersion

    The weightless compilation API gains explicit modes ("0" = NONE, "1" = EXTERNAL_ONLY, "2" = ALL), deprecating SetWeightlessEnabled and ep.enable_weightless.

    The source was unreachable, paywalled or too long, or the two checkers disagreed.

    The article says

    “ModelCompilationOptions_SetWeightlessMode and ep.enable_weightless_mode ("0" = NONE, "1" = EXTERNAL_ONLY, "2" = ALL”

    The source says

    No passage could be compared.

    Source cited by the article: github.com/microsoft/onnxruntime/pull/32899

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN —

Recorded for context only, checked 15 Nov 2026, 20:44 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 v1.32.0”

More on Rubric

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

  1. Score 0.75

    llama.cpp v1.0

  2. Score 0.71

    Announcing .NET 11