Sign in Subscribe

AI inference

Everything tagged AI inference.

Share your story Subscribe

Featured

Together AI says IBM Cloud B300 inference cluster is running

Together AI says IBM Cloud B300 inference cluster is running

DP News TeamOct 7, 2026

Antseed launches peer-to-peer marketplace for AI inference

Antseed launches peer-to-peer marketplace for AI inference

Iterate.ai launches Lifeboat inference engine for private AI agents

Iterate.ai launches Lifeboat inference engine for private AI agents

Latest

News
Meta sets 2027 deployments for MTIA 450 and MTIA 500 chips
Meta is lining up two in-house inference-chip deployments for 2027, targeting better energy and cost efficiency and less reliance on merchant…
DP News Team · 2w ago
News
Qualcomm and Amazon Agree to Develop Custom AI Chips for AWS
Qualcomm and Amazon agreed to develop custom AI inference silicon and optical interconnects for AWS data centers under a multi-generation…
DP News Team · 4w ago
News
Gimlet Labs raises $300 million Series B at $3 billion valuation
Gimlet Labs raised $300 million in a Series B led by Andreessen Horowitz. The round values the AI inference infrastructure startup at $3 billion as…
DP News Team · Sep 4
News
Cerebras unveils CS-4 wafer-scale inference system, claiming up to 30x GPU speed
Cerebras unveiled the CS-4, a wafer-scale inference system combining three WSE-3T processors, and said it runs large-model inference up to 30 times…
DP News Team · Aug 19
News
OpenAI previews Ultrafast tier running GPT-5.6 Sol up to 14x faster on Cerebras chips
OpenAI unveiled Ultrafast on August 13, a preview tier it says runs GPT-5.6 Sol up to 14 times faster on Cerebras' wafer-scale hardware.
DP News Team · Aug 13
News
AMD acquires Taalas, betting on AI chips with model weights etched into silicon
AMD agreed to acquire Taalas, a Toronto startup that etches AI model weights directly into silicon to cut inference costs, on August 6, 2026.
DP News Team · Aug 6
News
AMD and Cerebras partner on disaggregated AI inference, claiming 5x efficiency gain
AMD and Cerebras unveiled a disaggregated AI inference partnership claiming up to five times higher tokens per second per watt, launching first on…
DP News Team · Jul 23