Architect at Impala, an inference company specializing in latency-insensitive (async/batch) workloads; leads its batch product.
Appearances
Concepts
llm-inference · model-selection · open-weight-models · ai-hype
Architect at Impala, an inference company specializing in latency-insensitive (async/batch) workloads; leads its batch product.
llm-inference · model-selection · open-weight-models · ai-hype