Fused MoE Support #66084
Merged
Fused MoE Support #66084
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
你的PR提交成功，感谢你对开源项目的贡献! |
暂时先移除了bf16 wint8 wint4，后续组网完成后进行支持 |
qingqing01
reviewed
Jul 30, 2024
paddle/phi/kernels/fusion/cutlass/cutlass_extensions/gemm/kernel/gemm_moe_problem_visitor.h
Outdated
Show resolved
Hide resolved
paddle/phi/kernels/fusion/cutlass/cutlass_extensions/gemm/kernel/gemm_moe_problem_visitor.h
Show resolved
Hide resolved
yuanlehome
previously approved these changes
Jul 30, 2024
paddle/phi/kernels/fusion/cutlass/cutlass_kernels/moe_gemm/fused_moe_gemm_kernels_template.h
Outdated
Show resolved
Hide resolved
yuanlehome
approved these changes
Jul 31, 2024
Lans1ot
pushed a commit
to Lans1ot/Paddle
that referenced
this pull request
Aug 5, 2024
* [Feature] Fused MoE Support. * [Bugfix] Fix compile error. * [Bugfix] fix test error and compile error. * [Bugfix] fix compile error. * [Bugfix] remove bf16 * [Bugfix] fix compile error * [Bugfix] deal with float16 * [Bugfix] deal with float16 * [Bugfix] skip test if not gpu * [Refactor] add doc explain. * [Refactor] modify doc explain. * [Feature] add wint support * [Refactor] Refine doc. * [Refactor] fix CI problem * [Bugfix] fix error * [Feature] add bf16 * [Refactor] fix bf16 compile flag and docs * [Refactor] remove redundant code * [Refactor] refine code * [Refactor] doc refine * [Refactor] doc refine2 * [Bugfix] refine doc and code
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR Category
Inference
PR Types
New features
Description
Pcard-71501
新增Fused MoE融合优化，目前支持float16 bfloat16，后续增加wint8 wint4