Benchmark
InferenceMAX
An AI inference performance benchmarking framework developed by SemiAnalysis, designed to evaluate chip-level inference metrics such as token throughput and latency under real-world workload conditions.
Timeline (last 90 days)
Sep 24
Jalapeño testing used Semi Analysis's InferenceMAX framework with data provided by OpenAI; the full test suite was not completed, raw logs were not made public, and test scenarios were limited to 8K input and 1K output with speculative decoding disabled.
Unverified50%