mengceng15 opened a new pull request, #11586: URL: https://github.com/apache/tvm/pull/11586
Fix a minor problem with batch matmul quantization realize. If the two inputs are cast into the same data type, no vnni implementation will be added to batch_matmul x86 strategy. (In /python/tvm/relay/op/strategy/x86.py, function batch_matmul_strategy_cpu) -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
