This repository has been archived by the owner on Oct 25, 2024. It is now read-only.
Clean data #58
Merged
Clean data #58
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
* fix input_shape_recorder issue in SUT multi-ins * reset dispatch_config to empty under dynamic shapes * clean cpplint * fix typo
* add src1_perm in matmul python op * fix the matmul python op compatibility * fall back int8 weight matmul op type and clean the file format * fix transpose_batch_matmul pattern
* fix windows fail * disable jit kernel check in windows * add TODO for reference implementation * rename transpose matmul UT
* deallocation into deconstruction * refine cmake
Co-authored-by: ZhangJianyu <zhang.jianyu@outlook.com>
*update translnorm ref impl update benchmark & fix warning support s32 input data_type. calc_mean parallel modify clac_var modify test_spmm modify UT with append sum modify wordspace memory as input for multi thread Replace Intrinsics with JIT code package spmm+lnorm into layernomalized_spmm ker make KTile configable. add the compile for multihead attention stand-alone trans_mha tmp_buffer for all engine mha-operator support 2d case & add pseudo code on engine side fix windows compile fail, runtime-error and remove engine-side dead code. add 2 seq_cpy jit with dynamic size * unify bit_cast to avoid compiler error rename spmm variables for readness * unify amx configure --------- Co-authored-by: Hengyu Meng <hengyu.meng@intel.com>
Co-authored-by: yi1ding <yi1.ding@intel.com> Co-authored-by: Yu, Zhentao <zhentao.yu@intel.com> Co-authored-by: Bo Dong <bo1.dong@intel.com> Co-authored-by: Meng, Hengyu <hengyu.meng@intel.com> Co-authored-by: Wenxin Zhang <wenxin.zhang@intel.com> Co-authored-by: yuchengliu1 <yucheng.liu@intel.com>
This reverts commit ead0a15.
This reverts commit 222bfb8.
* Added example for finetuning Llama as chatbot. Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> * add flan-t5 finetuning codes with peft. * Update README.md * refined readme and code. Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> * add model content Signed-off-by: XuhuiRen <xuhui.ren@intel.com> * add model content Signed-off-by: XuhuiRen <xuhui.ren@intel.com> * added dataset concatenation option. Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> * Added generation code and refined readme. Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> * refined readme. Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> * added ccl backend. Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> * revision for readme Signed-off-by: XuhuiRen <xuhui.ren@intel.com> * revision for readme Signed-off-by: XuhuiRen <xuhui.ren@intel.com> * revision for readme Signed-off-by: XuhuiRen <xuhui.ren@intel.com> * revision Signed-off-by: XuhuiRen <xuhui.ren@intel.com> * revision Signed-off-by: XuhuiRen <xuhui.ren@intel.com> * revision Signed-off-by: XuhuiRen <xuhui.ren@intel.com> * revision Signed-off-by: XuhuiRen <xuhui.ren@intel.com> * revision Signed-off-by: XuhuiRen <xuhui.ren@intel.com> --------- Signed-off-by: Ye, Xinyu <xinyu.ye@intel.com> Signed-off-by: XuhuiRen <xuhui.ren@intel.com> Co-authored-by: Lv, Kaokao <kaokao.lv@intel.com> Co-authored-by: lkk <33276950+lkk12014402@users.noreply.github.com> Co-authored-by: XuhuiRen <xuhui.ren@intel.com>
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
Type of Change
dataset clean
Description
dataset clean
Expected Behavior & Potential Risk
none
How has this PR been tested?
no need
Dependency Change?
no