Edition of Monday 16 November 2026

GPU says 35% busy. Busy doing what?

Comments on “GPU says 35% busy. Busy doing what?”

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

Tensward, which builds an open-source LLM inference tuning tool, found that nvidia-smi's 35% "busy" figure on an H100 running llama.cpp hid a 643 MB per-request copy of conversation state off the GPU for a hybrid Qwen model. Disabling prompt caching and checkpoints raised throughput from 58 to 110 tokens per second, but it slowed a returning-conversation workload on an 8B model by about 20%. The figures are the company's own and unsourced; its CUPTI-based counter is research tooling, and its crash rate was only measured on one H100.

Read the original at tensward.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. 10 of 60 with a score of 0.68. The panel rated it highest on new information (0.90) and technical depth (0.90), lowest on significance (0.52).

AI judgeJudge 2claude-haiku-5-5
Detailed, measured engineering write-up on LLM inference GPU utilisation with reproducible flags and numbers; practical for builders, narrow audience, modest significance, some self-promotion of their tool.
AI judgeJudge 3gpt-5.6-luna
A well-supported engineering investigation measures hidden GPU memory-copy costs, explains CUPTI-based instrumentation, reports reproducible performance effects and limitations, and offers actionable diagnosis for LLM inference operators.

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

0.68total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.52
  • Reader interest0.82
  • Audience breadth0.53
  • Practical relevance0.81
  • Substantiated0.88
  • Technical depth0.90
  • New information0.90
  • Counts against: Promotional0.11
  • Counts against: Overclaim0.20

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?0.520.350.680.520.33+0.24+0.124
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.740.820.900.820.16+0.26+0.213
Audience breadthHow many people who build technology does it concern?0.450.500.650.530.20+0.13+0.069
Practical relevanceHow useful is it to someone who builds software or tech products?0.810.800.820.810.02+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.0.960.800.880.880.16+0.05+0.044
Technical depthHow technically substantive is it?0.990.880.830.900.17+0.05+0.045
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.850.900.960.900.11+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.0.040.200.080.110.16−0.19−0.020
OverclaimDo the headline or conclusions claim more than the body supports?0.180.300.120.200.18−0.11−0.022
Sum of contributions+0.677
Claim-check penalty0.000
Total, as published0.677

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 #10 on Rubric, 16 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-16/10/"><img src="https://rubric.hrih.si/badge/2026-11-16/10.svg" alt="Ranked #10 on Rubric, 16 Nov 2026" width="245" height="28"></a>

Claim check

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

  1. No source givenNumber

    nvidia-smi reported the H100 as 35% busy while the LLM server delivered 58 tokens per second and users waited almost two seconds for a first token.

    The article gives no link or citation for it.

    The article says

    “It said 35% busy. Throughput was 58 tokens per second, and users waited almost two seconds for a first token”

    The source says

    No source to compare with.

  2. No source givenGeneralization

    NVIDIA documents GPU utilisation as the share of each sampling period in which at least one kernel was running.

    The article gives no link or citation for it.

    The article says

    “NVIDIA documents it as the share of each sampling period in which at least one kernel was running”

    The source says

    No source to compare with.

  3. No source givenNumber

    With llama.cpp and Qwen3.8-27B, each request copied 643 MB from the GPU to host memory, versus 49 MB for a regular 8B model on the same prompts.

    The article gives no link or citation for it.

    The article says

    “Every request copied 643 MB from the GPU back to host memory. A regular 8B model on the same prompts copied 49 MB”

    The source says

    No source to compare with.

  4. No source givenCausal conclusion

    Disabling prompt cache and context checkpoints raised throughput from 58 to 110 tokens per second and busy from 35% to 88%.

    The article gives no link or citation for it.

    The article says

    “Throughput went from 58 to 110 tokens per second, and busy went from 35% to 88%”

    The source says

    No source to compare with.

  5. No source givenVersion

    On a newer llama.cpp build (b12246, from 10 November), the same workload ran 67 to 75% faster with default settings than on build b11669 (15 October).

    The article gives no link or citation for it.

    The article says

    “With default settings it ran the same workload 67 to 75% faster”

    The source says

    No source to compare with.

  6. Couldn’t checkCausal conclusion

    Three merged pull requests between the two llama.cpp builds changed how state is copied and stored.

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

    The article says

    “Between the two builds, three merged pull requests changed how state is copied and stored: #30881, #31391 and #30137”

    The source says

    No passage could be compared.

    Source cited by the article: github.com/ggml-org/llama.cpp/pull/30881

  7. No source givenNumber

    With vLLM on an H100, nvidia-smi read 95 to 97% busy while DCGM SM occupancy was 8 to 12%.

    The article gives no link or citation for it.

    The article says

    “nvidia-smi read 95 to 97% busy, while DCGM’s SM occupancy (DCGM_FI_PROF_SM_OCCUPANCY) was 8 to 12%”

    The source says

    No source to compare with.

  8. No source givenNumber

    nsys reported 639 MB copied per request, consistent with the census figure.

    The article gives no link or citation for it.

    The article says

    “we used it to check our figure (it said 639 MB”

    The source says

    No source to compare with.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 5 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 16 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 “GPU says 35% busy. Busy doing what?”

More on Rubric

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