Spaces:

ansh123456789
/

ragingoa

Running

App Files Files Community

ragingoa / benchmark

781 kB

Ctrl+K

Ctrl+K

1 contributor

History: 12 commits

ansh123456789's picture

docs: update README with accurate numbers, architecture, 4-tier guardrails and retrieval benchmark results

b5f9729 4 days ago

results
docs: update README with accurate numbers, architecture, 4-tier guardrails and retrieval benchmark results 4 days ago
quick_eval.py

1.98 kB
feat(perf): optimize latency to sub-60ms with BM25 hybrid fusion, INT8 quantization and 64-token bounding 5 days ago
report.py

6.86 kB
feat(core): complete voice-rag-indic pipeline with STT, FAISS HNSW, BM25 rerank, guardrails, FastAPI, benchmarks, and demo 7 days ago
run_cold_start_bench.py

8.5 kB
Optimize cold-start latency: batched prompt guard, eager startup warmup, and sub-200ms SLA enforcement 6 days ago
run_latency_bench.py

22 kB
fix(guardrails): multilingual cross-encoder reranker, theft/fraud regex, and cold-start optimization 5 days ago
run_speed_bench_50.py

14.1 kB
feat(optimizations): implement 7 low-latency non-LLM RAG adaptations and 750-query benchmark suite 6 days ago