# Inferact

> Markdown twin of https://roboterminal.app/companies/inferact · https://roboterminal.app/companies/inferact.md

## On shared sources

- [SemiAnalysis](https://roboterminal.app/companies/semianalysis) (5)
- [vLLM](https://roboterminal.app/companies/vllm) (5)
- [NVIDIA](https://roboterminal.app/companies/nvidia) (3)
- [AMD](https://roboterminal.app/companies/amd) (2)
- [Google](https://roboterminal.app/companies/google) (2)
- [Moonshot AI](https://roboterminal.app/companies/moonshot-ai) (1)
- [RadixArk](https://roboterminal.app/companies/radixark) (1)
- [Red Hat](https://roboterminal.app/companies/red-hat) (1)

## Pulse

- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2113054576844628113)
  Three teams in one month have pushed LLM decode forward with megakernels: Inferact on Google TPUs, AMD with TileRT and FlyDSL, and now NVIDIA on GB300, now live on InferenceX. We're excited to see the…
- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2111938013852762351)
  BREAKING NEWS🚨: @Inferact & Google submit their FIRST preliminary TPUv7 Kimi K3 2.8T Model Submission, and it is already delivering strong perf per TCO against GB200 NVL72, B300, and MI355 in the ult…
- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2111532833114054891)
  TOKENMAXXING: @vllm_project and @inferact achieve 1.3 BILLION tokens per $ of TCO (hyperscaler volume pricing) via disaggregated serving on AgentX. This result is 4x better than the B300 aggregated co…
- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2110496505031192895)
  ALERT🚨🚨: @vllm_project, @Inferact & NVIDIA TOOK CO-DESIGN TO THE EXTREME WITH A GB300 NVL72 INFERENCE OPTIMIZATION TO GET 🚀 7.2x 🚀 BETTER PERF PER TCO THAN LITERALLY EVERY OTHER AI CHIP, using an …
- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2101355922148782264)
  Many Google TPU customers are already asking Google for SemiAnalysis AgentX performance results, as customers are saying that it is a representative workload of their agentic inference traffic. We are…
- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2098501866401218813)
  On the Day 0 release of DeepSeekv4.1 Flash, NVIDIA vLLM works out of the box with zero issues across all 6 SKUs: H100, H200, B200, B300, GB200, GB300! Amazing work by the NVIDIA & Inferact teams! In c…
- [@SemiAnalysis_ on X](https://x.com/SemiAnalysis_/status/2097445137521524787)
  Spec Decoding (DSpark) finally works with Pipeline Parallelism in vLLM!! 🔥 A lot of the GPU poor/proletarian have been asking for this feature for a while now, but it took the recent Kimi K3's massiv…

---

Source: Roboterminal · https://roboterminal.app/companies/inferact.md