---
schema_version: '1.0'
id: news-20260814-79f9db
title: Kog is going deeper to squeeze more inference out of GPUs
url: https://techcrunch.com/2026/08/14/kog-is-going-deeper-to-squeeze-more-inference-out-of-gpus/
url_hash: 79f9db340c9be8f4b85ce42cae4d210496b8565d91b96ee237a0f5e026552473
canonical_url: https://techcrunch.com/2026/08/14/kog-is-going-deeper-to-squeeze-more-inference-out-of-gpus
source: techcrunch
category: news/tech
category_raw: tech
region: usa
tags:
- it_general
- it_tech
- it_ai
lang: en
published_at: '2026-08-14T14:50:11Z'
fetched_at: '2026-08-14T16:17:23.609613Z'
updated_at: '2026-08-14T16:20:34Z'
status: published
content_hash: null
content_changed_at: null
license_note: link-only
summary: null
summary_source: null
summary_en: null
summary_omitted_reason: license_restricted
redistribution: false
keywords_en:
- artificial intelligence
- Baltimore
- deeper
- going
- GPUs
- Inference
- it_ai
- it_general
- it_tech
- Kog
- more
- out
- Output Filter
- squeeze
- technology
entities_en:
- name: Baltimore
  type: location
- name: Inference
  type: method
- name: it_ai
  type: concept
- name: it_general
  type: concept
- name: it_tech
  type: concept
- name: Kog
  type: person
- name: Output Filter
  type: method
topics_en:
- artificial intelligence
- technology
numeric_facts: []
entities:
- name: Kog
  type: person
- name: Baltimore
  type: location
key_facts: []
related: []
related_auto:
- name: BestComputerMonitors2026
  type: content
  weight: 1.0
- name: ChatGPT
  type: concept
  weight: 1.0
- name: GLM-5.3
  type: content
  weight: 1.0
- name: Every Fucking Website
  type: other
  weight: 1.0
- name: Seven_books_I_keep_close
  type: content
  weight: 1.0
computed_at: null
sanitized_at: '2026-08-20T14:56:50.092484+00:00'
---

# Kog is going deeper to squeeze more inference out of GPUs

## TL;DR
（要約なし・原文はリンク先を参照 / No summary available; see the source link.）

## Key Points
- it_general / it_tech / it_ai

## Details
(本文なし。リンク先参照)

## Source
元記事: [Kog is going deeper to squeeze more inference out of GPUs](https://techcrunch.com/2026/08/14/kog-is-going-deeper-to-squeeze-more-inference-out-of-gpus/) — published 2026-08-14T14:50:11Z