Humming: Fast, Flexible Kernels for Quantized Inference

No. 33 of 245 · vllm.ai · vLLM Team · published 23 Oct 2026, 01:42 UTC · first published 21 Oct 2026 · 15 min read

Programming & dev tools
AI & machine learning
Hardware & devices
Release

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

Ant Group and the vLLM community have open-sourced Humming, a general-purpose kernel library for quantized inference. It supports NVIDIA GPUs from Turing onward plus some CUDA-compatible devices, handles many weight and activation formats for dense and MoE models, and reports better performance than vLLM Marlin, FlashInfer, and DeepGEMM on many…

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

Score

0.70total under rubric v2.0

Significance0.65
Reader interest0.80
Audience breadth0.61
Practical relevance0.86
Substantiated0.81
Technical depth0.90
New information0.94
Counts against: Promotional0.17
Counts against: Overclaim0.33

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

Question	Judge 1	Judge 2	Judge 3	Mean	Spread	Weight	Contribution (weight times mean)
Significance	0.72	0.45	0.78	0.65	0.33	+0.25	+0.162
Reader interest	0.78	0.72	0.90	0.80	0.18	+0.20	+0.160
Audience breadth	0.58	0.55	0.70	0.61	0.15	+0.10	+0.061
Practical relevance	0.89	0.80	0.88	0.86	0.09	+0.15	+0.128
Substantiated	0.94	0.70	0.78	0.81	0.24	+0.10	+0.081
Technical depth	0.91	0.85	0.95	0.90	0.10	+0.10	+0.090
New information	0.92	0.90	0.99	0.94	0.09	+0.10	+0.094
Promotional	0.07	0.25	0.18	0.17	0.18	−0.15	−0.025
Overclaim	0.30	0.40	0.28	0.33	0.12	−0.15	−0.049
Sum of contributions							+0.702
Claim-check penalty							0.000
Total, as published							0.702

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

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 3 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 24 Oct 2026, 08:53 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 and listed in its JSON. This one was scored under rubric v2.0; How ranking works describes the current rubric, v2.2.