You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "hamzaqureshi5 (via GitHub)" <gi...@apache.org> on 2025/08/11 06:16:43 UTC
[PR] Resolved #18196 [tvm]
hamzaqureshi5 opened a new pull request, #18203:
URL: https://github.com/apache/tvm/pull/18203
Implemented native GQA support in Relax, enabling efficient compilation and execution of modern transformer architectures such as LLaMA.
[GQA Paper](https://arxiv.org/abs/2305.13245)
This issue is now resolved and can be closed.
--
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-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [Relax][Op] Added GQA Attention Resolved #18196 [tvm]
Posted by "hamzaqureshi5 (via GitHub)" <gi...@apache.org>.
hamzaqureshi5 commented on PR #18203:
URL: https://github.com/apache/tvm/pull/18203#issuecomment-3176540901
Please review @tqchen
--
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-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [Relax][Op] Added GQA Attention Resolved #18196 [tvm]
Posted by "hamzaqureshi5 (via GitHub)" <gi...@apache.org>.
hamzaqureshi5 closed pull request #18203: [Relax][Op] Added GQA Attention Resolved #18196
URL: https://github.com/apache/tvm/pull/18203
--
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-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [Relax][Op] Added GQA Attention Resolved #18196 [tvm]
Posted by "tqchen (via GitHub)" <gi...@apache.org>.
tqchen commented on PR #18203:
URL: https://github.com/apache/tvm/pull/18203#issuecomment-3179134116
Thanks, we are integrating GQA from flashinfer integration and not sure if we need it for standard attention interface, and if the current form is the best form, given GQA may also have group size config
--
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-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org