pytorch

mirror of https://github.com/pytorch/pytorch.git synced 2025-11-11 22:34:53 +08:00

Files

Nicolas Macchioni 4375c2c534 Cleanup gpt_fast benchmark (#144517 )

This is an exact copy of https://github.com/pytorch/pytorch/pull/144484, I bricked the last PR running ghstack land :(

Pull Request resolved: https://github.com/pytorch/pytorch/pull/144517
Approved by: https://github.com/davidberard98, https://github.com/huydhn

2025-01-10 05:22:13 +00:00

benchmark.py

Cleanup gpt_fast benchmark (#144517 )

2025-01-10 05:22:13 +00:00

common.py

[GPT-fast] Support run spcific model or micro-benchmark (#143607 )

2024-12-20 19:58:07 +00:00

generate.py

Migrate from Tuple -> tuple in benchmarks (#144259 )

2025-01-07 04:09:52 +00:00

mixtral_moe_model.py

Reduce the number of layers for mixtral moe model to adapt CI memory limitation (#125608 )