#prefill
Live, measured metrics for the hashtag #prefill from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #prefill
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.
Day-by-day usage
measured · fosstodon.org (Mastodon public tags API) · fetched 2026-07-28 03:19 UTC0 uses by 0 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 2026-07-28 03:19 UTCLive pulse
measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-28 03:19 UTCEverything below is measured over the latest 8 public posts (spanning ~4814 hours).
Posting hours (UTC)
Languages: English (5) · Russian (2) · Korean (1)
Avg boosts / post: 0.1
Top of the latest posts
Полез в исходники vLLM, чтобы понять, почему один символ убивает prompt caching В первой части я вывел одно правило и предложил жить по нему: стабильное в начало, изменчивое в хвост , один символ в системном промпте обнуляет весь кэш. Прави
Avi Chawla (@_avichawla) LLM 추론에서 prefill과 decode 단계의 차이를 설명하는 트윗. 첫 토큰이 느리게 나오는 이유는 네트워크 지연이 아니라, 입력을 한 번에 처리하는 prefill과 이후 토큰을 순차 생성하는 decode라는 구조적 특성 때문이라고 짚는다. https://x.com/_avichawla/status/2071522418594861215 #llm #inference #prefill
#Intel's mysterious new datacenter #GPU is what Nvidia's #RubinCPX nearly was Intel clearly sees an opportunity to fill the #Prefill void. The company, which has grown closer to Nvidia since CEO Lip Bu Tan took the reins last year, hasn't s
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/prefill