pytorch

b7bd677e - [quant][gpu][core][bug fix] Added memset to CacheKey for quantized cudnn linear op (#76447)

[quant][gpu][core][bug fix] Added memset to CacheKey for quantized cudnn linear op (#76447) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/76447 See https://github.com/pytorch/pytorch/pull/76436. The same idea is applied here. Test Plan: ``` python test/test_quantization.py -k test_qlinear_cudnn ``` Reviewed By: jerryzh168 Differential Revision: D35970360 Pulled By: dzdang fbshipit-source-id: 452f0703d3c257638d2ef1e2467756aeed0ec8d4 (cherry picked from commit ff52d26ad477bd2c0529b627ea3cc763523f80e6)