GitLab

* Move template modification from nn to fastnn (#97)

* update out product mean test

* polish out product mean test and update linear test

* update test for layernorm, use both kernel

* support test without triton

* polish layernorm

* use current code

* move template modification to fastnn, restore template in nn

* re-organize fastnn

* update evoformer unit test

* Align results and update unit tests (#98)

* update out product mean test

* polish out product mean test and update linear test

* update test for layernorm, use both kernel

* support test without triton

* polish layernorm

* use current code

* move template modification to fastnn, restore template in nn

* re-organize fastnn

* update evoformer unit test

* update evoformer stack test

* update test

* update msa_att_row

* update msa_att_col

* update evoformer and evo-stack

* update evoformer

* update extramsa

* move model loading out of the loop

* finish template test

* update test

* Move template modification from nn to fastnn (#84)

* update out product mean test

* polish out product mean test and update linear test

* update test for layernorm, use both kernel

* support test without triton

* polish layernorm

* use current code

* move template modification to fastnn, restore template in nn

* re-organize fastnn

* update evoformer unit test

* move model out of function

* only test inference

* remove cache in build

* update test inference

* restore changes

* restore build changes

* update inference and evoformer stack

* fix some bug

* update test

* update evoformer stack test

* update test

* update test

* fix test

* update test

* update test

* update input embedder

* update embedder

* reset core

* update test

* support template multimer in inject_nn

* modify requirements, fix CI container

* fix format error

* remove torch1.11 kernel cache

* add cache back

* add CI, update Dockerfile

* remove useless loop in inference, add some comments to Attention

* update inference test and CI

* fix path

* add pytest for test env

* add einops install

* add cuda cache, loose the condition

* fixed bugs in softmax kernel and update unittest for softmax

* remove redundancy mask for softmax grad

* test both cuda/triton kernel in unittest

* update out product mean test

* polish out product mean test and update linear test

* update test for layernorm, use both kernel

* support test without triton

* polish layernorm

* use current code

Can get stable results now

* Update environment.yml

torch==1.11.1+cu113 is not supported in pip channel now

* update other version

* add torch version check

if torch version > 1.11.1, turn on tf32

* add triton kernel

* add softmax kernel

* fix bugs in triton kernel

* remove eviction_policy

* refactoring triton kernel for softmax

* update workflow store dir

* use global and usr name

* restore change

* update workflow document

* update monomer workflow store dir

* fix path format

* fix typo

* fix typo

* fix typo

* Update fastfold_data_workflow.py

* Update fastfold_data_workflow.py

* Update fastfold_data_workflow.py

* fix typo

update workflow store dir and readme

Use inplace to save memory

* update ops

* finish on 1 gpu

* update bug in incom mul

* update async broadcast

* update income

* add attention chunk

* finish embed

* align evoformer

* update embed

* align evoformer

* update embed

* update template

* update template

* update extramsa

* fix a bug

* update outerproductmean

* remove useless class

* fix a bug when chunk is None

* fix bug when chunk is None

* add multimer workflow

* support multimer dataworkflow

* support small_bfd with ray

* rm useless log

* add multimer inference

* add dada pipeline

* add import _weight

* add struct mudule

* support multimer datapipiline

* module for multimer

* support inference multimer

* add geometry

* delete unuseful code

* delete debug print

* add faster extraMSA and templateStack

* add license

* [ray] use ray for DB queries

* patched openmm

* add test exec script

* remove output before exec

* [tools] add coverage param to HHBlits

* [tools] add more param options to HHSearch

* [tools] remove ray from JackHmmer runner

* [tools] add comment for cov param in hhblits

* [tools] cleanup all debug code

* [tools] restore original files
Co-authored-by: shenggan <csg19971016@gmail.com>

Added data workflow for fastfold