Spaces:
Sleeping
Sleeping
Commit History
-
feat: add nfcorpus quality eval for fp32 vs INT8
Aditya KulkarniMeasure cosine drift, rank agreement, and nDCG/recall so INT8 is judged on embedding quality, not speed alone.c745c50
-
feat: land nfcorpus benches, encode batch_size, and INT8-negative docs
Aditya KulkarniPass max_batch_size through model.encode so 128/256/512 batches are one forward pass, not silently chunked at 32. Add file-sourced bench harness, prepare_dataset.py, and the 24-run latency/throughput matrix including dynamic INT8. Document the two-regime result and the INT8 slowdown. Keep nfcorpus text pools gitignored; they regenerate with a fixed seed.dfdc75f
-
test: add benchmarking suite and publish results
Aditya Kulkarni- run_matrix.py drives the full 16-config matrix (one server per config) - matrix spans cpu/mps, batch sizes 1-32, and pytorch vs onnx backends - naive_bench + utils add model-only and serving-overhead baselines - bench.py records the device in its output metadata - plot_results.py renders the batching sweep chart - results in benchmarks/README.md, methodology in benchmarks/ANALYSIS.md - surface the results in the project README72c62ed