#llminference

Live, measured metrics for the hashtag #llminference from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.

hashtag.org network · sponsored

Own #llminference

This #name is available to claim. It becomes your portal on the open agent web: this very page, a keyword you rank for by an open public stake, and a verifiable identity for AI agents. Nobody else sells a page like this for every #name.

$5.00/ year · 12-character #name
Claim #llminference — $5.00/yr→
Annual, renews each year
Buy on hashtag.space (web3)
one-timepay once, yours for life
card via hashtag.org · tokens via hashtag.space
5
Uses / 7 days
Mastodon
4
Accounts / 7 days
Mastodon
25
Recent posts
Mastodon
~0/hr
Recent pace
Mastodon · last 25
0
Avg reactions / post
Mastodon · last 25

Day-by-day usage

measured · fosstodon.org (Mastodon public tags API) · fetched 2026-07-27 05:33 UTC
2
07-21
0
07-22
1
07-23
1
07-24
0
07-25
1
07-26
0
07-27

5 uses by 4 unique accounts across the window. Real per-day counts, not estimates. Newest bar is today so far.

Related hashtags

measured · fosstodon.org (Mastodon public search API) · fetched 2026-07-27 05:33 UTC
#llminferencehandbook
0 uses · 0 accounts / 7d

Live pulse

measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-27 05:33 UTC

Everything below is measured over the latest 25 public posts (spanning ~7644 hours).

Posting hours (UTC) — busiest: 13:00

00:0012:0023:00

Languages: English (24)

Avg boosts / post: 0.2

Top of the latest posts

  • The AI world is buzzing over TurboQuant, Google Research’s new answer to the AI Memory Wall. This isn't just an incremental update; it’s a fundamental shift in how we think about hardware efficiency. By combining two new methods—PolarQuant

    BSR Tech News@[email protected]♥ 1↻ 12026-03-28 12:57 UTCView post →

  • TonoKen3Local LLM&Infrastructure Architectとのけん (@Tono_Ken3) GLM의 CPU 추론 속도가 7 TPS에서 13.5 TPS로 개선된 상황에서, 추론(thinking)은 영어 기반 표현으로 처리하고 실제 작업은 영어에 강한 Laguna-S-2.1로 분리하는 다중 모델 파이프라인을 실험하는 아이디어를 제시했다. 언어별 모델 강점과 병렬 처리량을 조합하려는 에이전트 설계 관점의 제안이다.

    ainews@[email protected]♥ 0↻ 02026-07-26 05:48 UTCView post →

  • Karl Freund (@karlfreund) AMD와 Cerebras가 협력해 대규모 컴퓨팅과 저지연 추론을 결합한 AI 인프라 대안을 제공한다고 발표했다. 특히 LLM 추론의 prefill과 decode 단계 성능을 겨냥하며, Nvidia 및 Groq에 대한 경쟁 구도로 제시됐다. 올해 후반 제공 예정이다. https://x.com/karlfreund/status/2080349408303153199 #aiinfrastruc

    ainews@[email protected]♥ 0↻ 02026-07-24 06:54 UTCView post →

Every number above is measured from a named public API at the shown fetch time. Nothing is estimated or extrapolated. Platforms that lock their data behind paid APIs are not shown. Agents: the same numbers, as JSON, at /api/hashtags/llminference