ONNX Runtime GenAI model builder README

Fields

id

sources/qlab2-ortgenai-model-builder

URL

https://github.com/microsoft/onnxruntime-genai/blob/main/src/python/py/models/README.md

Publisher

Microsoft

Kind

repo

Accessed

2026-10-03

notes

The ORT-GenAI quant paths: -p int4 with an already-AutoGPTQ/AutoAWQ-quantized PyTorch checkpoint, -p precision with a dense checkpoint, direct GGUF F16/F32 input, plus --extra_options use_webgpu_fp32, use_cuda_bf16, accuracy_level, matmulnbits_block_size, qmoe_block_size, qmoe_weights_prepacked, is_symmetric, use_qdq_pattern, int8_bit_placement, and quantized-KV-cache options. | SOURCE AUDIT 2026-10-03: the 'published' field held a verbatim copy of this notes paragraph instead of a date (field corruption across the qlab2-* batch); published set to null because a GitHub README, doc page or source header has no reliable publication date of its own. Content of the document itself was re-verified live 2026-10-03 and the notes are correct.

Notes

The ORT-GenAI quant paths: -p int4 with an already-AutoGPTQ/AutoAWQ-quantized PyTorch checkpoint, -p precision with a dense checkpoint, direct GGUF F16/F32 input, plus --extra_options use_webgpu_fp32, use_cuda_bf16, accuracy_level, matmulnbits_block_size, qmoe_block_size, qmoe_weights_prepacked, is_symmetric, use_qdq_pattern, int8_bit_placement, and quantized-KV-cache options. | SOURCE AUDIT 2026-10-03: the 'published' field held a verbatim copy of this notes paragraph instead of a date (field corruption across the qlab2-* batch); published set to null because a GitHub README, doc page or source header has no reliable publication date of its own. Content of the document itself was re-verified live 2026-10-03 and the notes are correct.

Cross-references

This record references no other records.