#InferenceX
2 articles with this tag
Technology
Same B200 can deliver 50% more output depending on operator
SemiAnalysis analyst Oliver Kennon showed AI Engineer how tuning and operation can lift B200 output 50% and why that defines cost per useful token.
3 days ago
Semiconductors
OpenAI Jalapeño inference chip lands soon
OpenAI's Jalapeño inference chip promises 1.5-1.9x throughput per watt with deployment by year-end, but no prediction market yet prices the rollout.
about 2 months ago
