#dspark
Live, measured metrics for the hashtag #dspark from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #dspark
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 2026-07-27 05:20 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 2026-07-27 05:20 UTCNo related tags with measured usage found for #dspark.
Live pulse
measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-27 05:20 UTCEverything below is measured over the latest 9 public posts (spanning ~392 hours).
Posting hours (UTC)
Languages: English (4) · German (2) · Russian (1) · Spanish (1)
Avg boosts / post: 0
Top of the latest posts
AISatoshi (@AiXsatoshi) Kimi 시리즈 추론 가속용 DSpark가 공개되었고, Kimi-K2.6의 평균 처리량은 2.55배(+155%), Kimi-K2.7-Code는 2.36배(+136%) 향상됐다고 밝혔다. Kimi 계열 서빙 최적화에 바로 참고할 만한 성능 개선 소식이다. https://x.com/AiXsatoshi/status/2076696910543601685 #dspark #kimi #inferen
DSpark на двух DGX Spark: порт, баг на одну строку и бенчмарки, которые пришлось мерить заново DeepSeek выпустил DSpark — спекулятивный декодер для V4. В окне 27–30 июня 2026 рабочего публичного пути для GB10 не было — мы портировали его са
RT @Yuchenj_UW: DeepSeek ist das GOAT. 🐳 Sie haben gerade DSpark veröffentlicht, eine neue Methode des spekulativen Decodierens, die den Durchsatz um 51% auf 400% steigert. Sie haben außerdem DeepSpec, das Trainingsframework dahinter, als
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/dspark