[Paddle-Inference] support preln-ernie: add preln_emb_eltwise_layernorm_op, preln_skip_layernorm_op #39570
Conversation
This file contains 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
|
Thanks for your contribution! |
| #if IS_TRT_VERSION_GE(7000) | ||
| VLOG(4) << "convert fluid PrelnEmbEltwiseLayerNorm op to tensorrt layer"; | ||
|
|
||
| if (!(engine_->use_oss() && engine_->with_interleaved())) { |
There was a problem hiding this comment.
能否把判断放到pass部分，这样即便跑不了trt plugin，也不会挂掉。
| const framework::Scope& scope, bool test_mode) override { | ||
| #if IS_TRT_VERSION_GE(7000) | ||
| VLOG(4) << "convert fused preln_skip_layernorm op to tensorrt layer"; | ||
| if (!(engine_->use_oss() && engine_->with_interleaved())) { |
| @@ -1007,6 +1009,24 @@ bool OpTeller::Tell(const framework::ir::Node* node, bool use_no_calib_int8, | |||
| } | |||
| } | |||
|
|
|||
| if (op_type == "fused_preln_embedding_eltwise_layernorm") { | |||
There was a problem hiding this comment.
如果没有进入trt，该融合pass没有原生kernel实现，运行时会报错。所以判断是否可以提前到pass阶段？如果不可以，这里可以直接报错了，信息会更明确
| @@ -1316,6 +1336,17 @@ bool OpTeller::Tell(const framework::ir::Node* node, bool use_no_calib_int8, | |||
| } | |||
| } | |||
|
|
|||
| if (op_type == "preln_skip_layernorm") { | |||
好的~ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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 types
Others
PR changes
Others
Describe
支持 preln 结构的ernie模型，增加 preln_emb_eltwise_layernorm_op, preln_skip_layernorm_op 两个op