inference-server / scripts

Commit History

feat: add nfcorpus quality eval for fp32 vs INT8
c745c50

Aditya Kulkarni commited on

feat: land nfcorpus benches, encode batch_size, and INT8-negative docs
dfdc75f

Aditya Kulkarni commited on

feat: add INT8 ONNX quantization with configurable backend file
275b8e5

Aditya Kulkarni commited on

test: add benchmarking suite and publish results
72c62ed

Aditya Kulkarni commited on

feat: add ONNX backend support
f864c14

Aditya Kulkarni commited on

cleanup: renamed api endpoint /predict to /embed
d690983

Aditya Kulkarni commited on

feat: add dynamic batching and benchmark script
046db3f

Aditya Kulkarni commited on