#tensorrtllm
Live, measured metrics for the hashtag #tensorrtllm from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #tensorrtllm
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 · mastodon.online (Mastodon public tags API) · fetched 2026-09-29 22:12 UTC0 uses by 0 unique accounts across the window. Real per-day counts, not estimates. Newest bar is today so far.
Related hashtags
measured · mastodon.online (Mastodon public search API) · fetched 2026-09-29 22:12 UTCNo related tags with measured usage found for #tensorrtllm.
Live pulse
measured · mastodon.online (Mastodon tag timeline) · fetched 2026-09-29 22:12 UTCEverything below is measured over the latest 8 public posts (spanning ~14144 hours).
Posting hours (UTC)
Languages: English (6) · Russian (1) · German (1)
Avg boosts / post: 0.1
Top of the latest posts
Poolside (@poolsideai) Poolside가 Laguna S 2.1에서 일부 사용자가 겪은 추론 중 반복 루프 문제를 수정했다. 원인은 DFlash와 TensorRT-LLM의 상호작용, 그리고 잘못된 기본 temperature 설정으로 파악됐다. TensorRT-LLM 기반 LLM 서빙에서 디코딩 파라미터와 런타임 조합이 출력 안정성에 영향을 줄 수 있음을 보여준다. https://x.com/poolsideai/
NVIDIA (@nvidia) NVIDIA 플랫폼 위에서 Dynamo, SGL, TensorRT LLM, vLLM 같은 오픈소스 및 추론 도구들이 지속적으로 최적화되고 있다고 밝혔다. 개발자 생태계의 개선을 통해 토큰 출력 품질과 비용 효율이 계속 향상된다는 점이 핵심이다. https://x.com/nvidia/status/2041932953698075086 #nvidia #opensource #tensorrtllm #vllm
NVIDIA (@nvidia) NVIDIA GB300 NVL72와 코드사인 소프트웨어 스택(NVIDIA Dynamo 및 TensorRT-LLM)이 NVIDIA Hopper 플랫폼 대비 와트당 성능을 50배 이상 향상시킨다고 발표했습니다. 전력 효율 중심의 대규모 추론 개선을 주장하는 내용입니다. https://x.com/nvidia/status/2023448139190202479 #nvidia #gb300 #powereffic
#tensorrtllm across platforms
every network with a public tag surfaceFollow #tensorrtllm straight to each platform’s own tag page. Where a platform publishes open data we measure it above; the rest lock their numbers behind paid APIs, so we link rather than guess.
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/tensorrtllm