Spaces:

Ypeng12
/

InferRoute

Sleeping

App Files Files Community

InferRoute / benchmarks

9.87 MB

Ctrl+K

1 contributor

History: 7 commits

Ypeng12

docs: add mathematical formulas, quality retention algorithm, and individual prompt evaluation examples

9b3fae3 5 days ago

datasets
feat: integrate allenai/WildChat-4.8M as flagship real dataset & update 10k benchmark results 5 days ago
results
docs: add mathematical formulas, quality retention algorithm, and individual prompt evaluation examples 5 days ago
evaluate_quality.py

4.22 kB
feat: implement learned router and reproducible benchmark harness 27 days ago
fetch_hf_real_datasets.py

5.32 kB
feat: integrate allenai/WildChat-4.8M as flagship real dataset & update 10k benchmark results 5 days ago
generate_10k_dataset.py

4.71 kB
feat: add HF real workload datasets (10k), streaming benchmark results, and BYOK budget tests 5 days ago
llm_router_bench.py

9.91 kB
feat: integrate 9 academic routing policies as explicit selectable gateway strategies and add benchmarking harness 17 days ago
plot_results.py

10.6 kB
feat: implement server-side FrugalGPT cascade router, prompt adaptation, and offline Pareto sweeps 24 days ago
run_10k_simulation.py

9.05 kB
fix: populate live analytics dashboard with real WildChat 10k benchmark metrics 5 days ago
run_hf_stream_benchmark.py

9.72 kB
feat: add HF real workload datasets (10k), streaming benchmark results, and BYOK budget tests 5 days ago
run_router_eval.py

7.81 kB
feat: implement server-side FrugalGPT cascade router, prompt adaptation, and offline Pareto sweeps 24 days ago
stream_hf_eval.py

4.4 kB
feat: add HF real workload datasets (10k), streaming benchmark results, and BYOK budget tests 5 days ago
train_router.py

8.42 kB
feat: integrate 9 academic routing policies as explicit selectable gateway strategies and add benchmarking harness 17 days ago