Sarvam AI Launches Token Factory: India-Hosted Inference for Open Models
itsOmSarraf_ · x · 2026-11-16
Sarvam AI launched Sarvam Token Factory in GA, hosting its own models and top open-weight models in India for chat, code, co-work, and soon cyber use cases. Data residency rules had kept many Indian teams off the best open models. The company claims cost and reliability matching global inference providers via kernel optimization, three-tier KV caching, and datacenter-scale GPU management.
More from Infra
- BIS Issues Interim Final Rule Addressing Remote Access to Advanced AI Chips — apples_jimmy · 2026-11-16
- Jailbroken PS4 runs a 9B open-source model at up to 43 tok/s by talking directly to its 2013-era GPU — AIFlow_ML · 2026-11-16
- Mobile AI Factory: agents auto-build on-device SLMs with 19x less GPU time — pmttyji · 2026-11-16
- Stratechery's Fictional Obituary: Imagining Jensen Huang's 2026 Exit From Nvidia — Gregory_C_Allen · 2026-11-16
- vLLM serves DeepSeek V4.1-Flash at 954K tokens/s per GPU, $38.96/GPU-hour on GB300 NVL72 — bookwormengr · 2026-11-16
- Colossus 2's 1.2M B200s could generate ~$400B/year in tokens at DeepSeek Flash rates — bookwormengr · 2026-11-16