[fleet exe] supprot fp16 feed and fetch on cpp side #39758
Merged
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
| @@ -52,6 +52,8 @@ bool LoadDataFromDistModelTensor(const DistModelTensor &input_data, | |||
| input_tensor_ptr = input_tensor->mutable_data<float>(dims, place); | |||
| } else if (input_data.dtype == DistModelDataType::INT32) { | |||
| input_tensor_ptr = input_tensor->mutable_data<int32_t>(dims, place); | |||
| } else if (input_data.dtype == DistModelDataType::FLOAT16) { | |||
| input_tensor_ptr = input_tensor->mutable_data<float16>(dims, place); | |||
| @@ -503,9 +507,13 @@ bool DistModel::FetchResults(std::vector<DistModelTensor> *output_data, | |||
| } else if (type == framework::proto::VarType::INT32) { | |||
| rst = FetchResult<int32_t>(fetch, output); | |||
| output->dtype = DistModelDataType::INT32; | |||
| } else if (type == framework::proto::VarType::FP16) { | |||
| rst = FetchResult<float16>(fetch, output); | |||
| // Note: use same enum number of float16 in numpy. | ||
| // import numpy as np | ||
| // print np.dtype(np.float16).num # 23 | ||
| constexpr int NPY_FLOAT16_ = 23; |
There was a problem hiding this comment.
NPY_FLOAT16是不是numpy的一个枚举
There was a problem hiding this comment.
是，但是拿不到这个enum，只能用enum对应的int来弄了。就是说以后如果numpy改了enum的顺序，这个hard code的值要跟着改。。。
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Outdated suggestions cannot be applied.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
support fp16 feed and fetch