Sarvam launches India-hosted Token Factory, shares how it 2x'd inference speed
itsOmSarraf_ · x · 2026-11-17
Indian AI company Sarvam has launched Token Factory, hosting its own models and a range of top open-weight models in India, matching leading inference providers on performance and reliability and offering enterprises a lock-in-free AI stack.
Alongside the launch, the team explains that a B200 cluster plus HF weights alone is far from enough: a long video walks through the engineering behind doubling serving speed on the same hardware, covering the inference engine, caching, and control-plane layers.
More from coding & agent
- Clare Liguori to lead AWS reInvent Developer keynote on Nov 30 — FlolightC · 2026-11-17
- REA-Video skill lets Claude reverse-engineer video editing styles; rival claims 20x speed at SSIM 0.96 — toolstelegraph · 2026-11-17
- Developer retries Amp Code after months and finally gets the hype: "completely different" — g3off_who · 2026-11-17
- Dev shares 5 AI automations for service businesses that actually make owners money — Crazy-Movie7633 · 2026-11-17
- SNEWPapers launches remote MCP turning AI tools into US newspaper archive researchers — Jolly-Newspaper-6769 · 2026-11-17
- Team designing open-source mock MCP server, asks community for testing pain points first — OkSkirt1039 · 2026-11-17