Add some gptq related args to quantize function (#2577)
Summary: Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * __->__ https://github.com/pytorch/executorch/issues/2577 Test Plan: Manully verified locally that the args passed through to quantize function `python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w-gptq -X -d fp32 -G 2568 --calibration_tasks wikitext fads --calibration_seq_length 1288 --calibration_limit 5123` Pull Request resolved: https://github.com/pytorch/executorch/pull/2577 python3 -m examples.models.llama2.export_llama -c stories110M.pt -p params.json -qmode 8da4w-gptq -X -d fp32 -G 2568 --calibration_tasks wikitext fads --calibration_seq_length 1288 --calibration_limit 5123 Reviewed By: Jack-Khuu Differential Revision: D55250463 Pulled By: jerryzh168 fbshipit-source-id: bdf1299952c1f1010a39849bcf70f398bddfce06
J
Jerry Zhang committed
2d8fa1f13211e48b935e01e687a126a4d37a3440
Parent: ba920e4
Committed by Facebook GitHub Bot <facebook-github-bot@users.noreply.github.com>
on 3/22/2024, 9:15:32 PM