llm-jp-4-8b-instruct-NVFP4 / quantization_recipe /scan_weight_scale_nan.py

Commit History

Improved calibration (strict-format slice), modelopt 0.45, vLLM 0.24 validation, plugin fixes (adjust_request scoping, extract_content_ids, indentation), full reproducibility bundle (pinned revision, env freeze, calibration file), LICENSE
7484310
verified

ege-g commited on