feat: add nfcorpus quality eval for fp32 vs INT8

chore: add pyright CI and use get_running_loop

feat: landing server-status panel and embed ttft/ttfr

feat: add HTML landing page for the Spaces App tab

feat: add /metrics snapshot and demote dead live-demo badge

chore: keep local SUMMARY.md off the repo

feat: land nfcorpus benches, encode batch_size, and INT8-negative docs

feat: add INT8 ONNX quantization with configurable backend file

feat: add readiness /health and structured request logging

feat: add input validation, backpressure, and request timeouts

test: add pytest suite and CI

test: add benchmarking suite and publish results

docs: overhaul project README

feat: add ONNX backend support

fix: interpret batch wait timeout in milliseconds

cleanup: renamed api endpoint /predict to /embed

Merge pull request #3 from BeardedAmbivert/feat/dynamic-batching

add HF Spaces metadata

Merge pull request #2 from BeardedAmbivert/feat/dynamic-batching

feat: add Dockerfile for HF Spaces

Merge pull request #1 from BeardedAmbivert/feat/dynamic-batching

feat: add dynamic batching and benchmark script

feat: add POST /predict endpoint with MiniLM embedding generation

Initial commit