Sarvam (reported by MarkTechPost) · India-hosted Inference Platform

Sarvam Token Factory

Sarvam Token Factory is a managed inference platform from Sarvam that serves its own Sarvam 105B model and several open-weight models, including GLM 5.3, DeepSeek V4.1 Flash, Kimi K3.1 Pro and Gemma 4 31B, from GPU clusters in India. Developers reach every model through one OpenAI-compatible API, and the stack uses a cache-aware router, separate prefill and decode GPU pools, and a shared Mooncake-based cache. Sarvam reports gains such as 1.9x per-GPU throughput over InferenceX on Kimi K3.1 Pro, but all benchmark figures are self-reported and Together AI is faster on one DeepSeek test.

Open the source ↗

Similar Developer Tools releases

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.