SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving
We introduce SWE-Serve, a benchmark for evaluating agents on production inference engineering tasks. Implementing an inference feature can require coordinating multiple changes across the serving stack, including model support, runtime execution, and public APIs. Existing benchmarks provide limited coverage of producti...
Jennifer Williams, David P. Farris, Jeffrey J. Farris et al.
· 0 citations