Loading activity…
@wafer_ai
continual inference optimization trusted by @vercel, @tavus, @brilliantorg, @ycombinator and 1500+ others
AI
Wafer says its GLM-5.2 deployment delivered 31% lower average model latency than GPT-4.1 mini on OpenAI and 44% lower than Gemma 4 31B on Cerebras in YC’s comparison.
AI
Wafer says the first resource uses worked problems to connect model dimensions to deployment choices, including memory capacity, workload distribution and expected performance under stated assumptions.
AI
Evan Conrad notes quiet ramping of GPU cluster volume over years.
AI
Thread begins deep dives into resources from new GitHub repository on inference optimization.
AI
The inference startup secured funding from MarathonMP and Chemistry among others.
