You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "Hzfengsy (via GitHub)" <gi...@apache.org> on 2023/09/12 11:41:47 UTC
[GitHub] [tvm] Hzfengsy opened a new pull request, #15730: [DLight] Update GEMV rule to support Adreno outer reduction
Hzfengsy opened a new pull request, #15730:
URL: https://github.com/apache/tvm/pull/15730
As Adreno has poor shared memory performance, for LLM workloads, we prefer `q4f16_0` instead of `q4f16_1`.
This PR adds GEMV rule support for Adreno outer reduction, comparing with `q4f16_1`, we get a performance gain
- Prefill(not related with this PR changes): 3636.6501 ms -> 1241.9469 ms
- Decode: 211.0834 ms -> 174.9357 ms
--
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
[GitHub] [tvm] Hzfengsy merged pull request #15730: [DLight] Update GEMV rule to support Adreno outer reduction
Posted by "Hzfengsy (via GitHub)" <gi...@apache.org>.
Hzfengsy merged PR #15730:
URL: https://github.com/apache/tvm/pull/15730
--
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