cameron quilici

T3 · host / generalist

Co-host of SemiAnalysis podcast and co-developer of InferenceX. Focuses on agentic benchmark design, KV cache offloading strategies, and real-world inference performance modeling.

1 call·1 name·0% bull·last heard 4 months ago·SemiAnalysis
track record

no scored calls yet — needs a stated position or a categorical verdict, with a matured window vs SPY

top calls

highest conviction · one per company
1stmedium conviction
$AMDAdvanced Micro Devices

AMD MI355X HBM advantage may close gap with prefix caching but trails Nvidia today

AMD's MI355X offers 1.5x HBM capacity versus Nvidia's B200, which could enable better prefix caching performance in multi-turn workloads, but current InferenceX benchmarks show Nvidia surpassing AMD across almost all aspects.

most discussed · click a bar to filter

recurring themes

1 total
$AMD
···
Advanced Micro Devices
MEDcameron quilici·SemiAnalysis·4 months ago
AMD MI355X HBM advantage may close gap with prefix caching but trails Nvidia today
AMD's MI355X offers 1.5x HBM capacity versus Nvidia's B200, which could enable better prefix caching performance in multi-turn workloads, but current InferenceX benchmarks show Nvidia surpassing AMD across almost all aspects.
"AMD MI355X versus B200, MI355 has one and a half times the HBM band capacity. So with prefix caching, right, like we'd expect it to to do to do better possibly."
6:43