Re: [PR] [Unity][Cutlass] Fix C source generation of dense operation [tvm]

vinx13 merged PR #16476: URL: https://github.com/apache/tvm/pull/16476 -- 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: commits-unsubscr...@tvm.apache.or

Re: [PR] [Unity][Cutlass] Fix C source generation of dense operation [tvm]

churvey commented on code in PR #16476: URL: https://github.com/apache/tvm/pull/16476#discussion_r1584157146 ## python/tvm/contrib/cutlass/gen_tensor_op.py: ## @@ -566,7 +566,10 @@ def get_flattened_batch_dim(arg_name, batch_rank): transposed = "transposed" in func_name

Re: [PR] [Unity][Cutlass] Fix C source generation of dense operation [tvm]

creaiter commented on code in PR #16476: URL: https://github.com/apache/tvm/pull/16476#discussion_r1473645951 ## python/tvm/contrib/cutlass/gen_tensor_op.py: ## @@ -566,7 +566,10 @@ def get_flattened_batch_dim(arg_name, batch_rank): transposed = "transposed" in func_nam

Re: [PR] [Unity][Cutlass] Fix C source generation of dense operation [tvm]

yelite commented on code in PR #16476: URL: https://github.com/apache/tvm/pull/16476#discussion_r1468035951 ## python/tvm/contrib/cutlass/gen_tensor_op.py: ## @@ -566,7 +566,10 @@ def get_flattened_batch_dim(arg_name, batch_rank): transposed = "transposed" in func_name

Re: [PR] [Unity][Cutlass] Fix C source generation of dense operation [tvm]

vinx13 commented on code in PR #16476: URL: https://github.com/apache/tvm/pull/16476#discussion_r1468000349 ## python/tvm/contrib/cutlass/gen_tensor_op.py: ## @@ -566,7 +566,10 @@ def get_flattened_batch_dim(arg_name, batch_rank): transposed = "transposed" in func_name

[PR] [Unity][Cutlass] Fix C source generation of dense operation [tvm]

creaiter opened a new pull request, #16476: URL: https://github.com/apache/tvm/pull/16476 It seems there is an issue while generating c source of dense operation using cutlass. Even though the dense operation contains bias parameters, the generated c code doesn't reflect that bias correc

Re: [PR] [Unity][Cutlass] Fix C source generation of dense operation [tvm]

creaiter commented on PR #16463: URL: https://github.com/apache/tvm/pull/16463#issuecomment-1911649513 Okay! I'm going to reopen this PR to the `main`. I noticed that the second issue already resolved, thus the reopened PR will only contain the change of the first issue. -- This is

Re: [PR] [Unity][Cutlass] Fix C source generation of dense operation [tvm]

creaiter closed pull request #16463: [Unity][Cutlass] Fix C source generation of dense operation URL: https://github.com/apache/tvm/pull/16463 -- 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 spe

Re: [PR] [Unity][Cutlass] Fix C source generation of dense operation [tvm]

masahi commented on PR #16463: URL: https://github.com/apache/tvm/pull/16463#issuecomment-1908867323 You can now send a PR to the `main`. Can you switch a branch or reopen? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and u

[PR] [Unity][Cutlass] Fix C source generation of dense operation [tvm]

creaiter opened a new pull request, #16463: URL: https://github.com/apache/tvm/pull/16463 It seems there are two issues while generating c source of dense operation using cutlass. 1. Even though the dense operation contains bias parameters, the generated c code doesn't reflect that b