Scs trans match #7307
Merged
Scs trans match #7307
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
…into scs_trans_match
|
Thanks for your contribution! |
…into scs_trans_match
zhupengyang
approved these changes
Oct 19, 2021
newway
added a commit
to newway/Paddle-Lite
that referenced
this pull request
Oct 19, 2021
newway
added a commit
to newway/Paddle-Lite
that referenced
this pull request
Oct 19, 2021
newway
added a commit
to newway/Paddle-Lite
that referenced
this pull request
Jan 5, 2022
zhupengyang
pushed a commit
that referenced
this pull request
Jan 17, 2022
* [XPU] change match_matrix_tensor op from old version to refector verison (#7012) * [XPU] change sequence concat op from old version to refector verison (#6847) * [XPU] change sequence_reverse api from old version to refector version (#6798) * [XPU] fix some bugs for transformer (#7014) * [XPU] Mul quant (#6850) * [XPU] bugfix on fc max (#7152) * expand_v2 supports dynamic shape (#7116) * [XPU] change search_noaligned_mat_mul op to fc_batched_vsl op (#7081) * [xpu] support qkv-fused weight reuse in scs_tran_match (#7293) * [XPU] Scs trans match (#7307) * [XPU] add lod_array_length; argmax support int32 (#7314) * [XPU] change fc_int16 op to fc_fusion (#7029) * [XPU] super big ernie support (#7184) * [XPU] free default workspace of xpu_ctx before setting up a new gm workspace (#7422) * [XPU] use get_max_ptr function (#7482) * [xpu] Fc int31 (#7514) * [xpu] fix continuous encoder fuse and fc max size * [xpu] refactor fc int31 for KL2 * use get_max_ptr function (#7529) * add activation xpu gelu (#7527) * [xpu] more check with multi_encoder pass (#7593) * [XPU]use get_max_ptr_size in search attention op (#7528) * [XPU]use get_max_ptr_size in bigru op (#7498) * [XPU] change sequence_topk_avg_pooling op from old version to refector verison (#7411) * update xpu api sequence_unpad (#7640) * update xpu api l2_norm (#7724) * [XPU] __xpu__resnet_fuse_pass should not match ResNeXt50 (#7824) * [xpu] support encoder mul shape without equal length and more check (#7753) * [XPU] use new search_varconv (#7865) * [XPU] use new sequence_topk_avg_pooling (#7834) * [XPU] fix xpu memory leak bug for arm arch (#8010) * [XPU] new new op in mmdnn (#7998) * [XPU] fix xpu l2_norm bug (#7983) * [XPU] grnn_cell op in mmdnn (#8139) * [XPU] use new concat in mmdnn (#8184) * [XPU] build 2.10 depending on new xpu_sdk_url: xdnn 2.3.0 and xre 4.0.7.1
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.
No description provided.