GPTQ Quantization / Test GPU

Fix fp16 ONNX detection for decoder models #49

Sign in to view logs

Triggered via pull request August 11, 2023 15:59

fxmarty

opened #1276

fxmarty:fix-fp16-ort-bug

Status Skipped

Total duration 13s

Artifacts –

test_gptq.yml

on: pull_request

Start self-hosted EC2 runner

Stop self-hosted EC2 runner