… too

…nges in the readme

* [ add ] vat_matmul runtime files

* [ update ] get rid of pushing 0s to ACC

* add comment about the change in codegen.cc

* restore ACC buffer initialization

* [ add ] compute missing fields of VTA config

…again)

* change to uint8_t in ila runtime

* [ refactor ] pre-compile to ILA asm

* [ impl ] jit

* [ add ] mlp model

* [ add ] quantized model in PT

* [ fix ] run quantized

* [ refactor ] AoT compiler

* hmm? I dont remember I touched this file

* [ fix ] naming issue and resolve some warnings

* [ fix ] turn off size check

* [ refactor ] cast according to annotation

* [ fix ] dtype

…(#3)

* integrate 3la driver into tvm framework

* lstm flexnlp backend driver added

* remove redundant submodule in the python test folder; redirect python driver path inside TVM in the ilaflex_runtime

* flexnlp lstm end-to-end flow complete

* end-to-end codegen for ILA-VTA

* [ add ] tests

* ignore instr_log

* tweak PR

* get rid of warnings

* remove logging in pattern matching

* [ add ] instruction for running the end-to-end test script

* [ init ] bias add codegen

* add data loading

* [ add ] bias add test case

* [ fix ] datatype conversion

* change to int8 inputs

* integrate 3la driver into tvm framework

* lstm flexnlp backend driver added

* [ init ] relu runtime

* [ add ] relu runtime code

* Add exact matcher

* fix data loading

* [ update ] tests

* [ refactor ] code

* [ add ] comments

* remove redundant submodule in the python test folder; redirect python driver path inside TVM in the ilaflex_runtime

* Simplify implementation, correct pattern bugs, and add more tests

* flexnlp lstm end-to-end flow complete

* Correct inaccurate comment

* Reformat comment

* Throw in refs because why not

* Need to visit matched args to find all matches

* Move utility checkers to exact_matcher file (they will come in handy again)

* Add test scaling the pattern matching to the speech-to-text model

* Unused function

* Add test case of not matching free var in match block

* Incorrect dimension

* set ila driver as external python scripts located through /home/leeoh/3la/pattern_matching/3la_ILA_tensor_op/ path

* 3la flexnlp python driver as standalone path; small fixed in include module in flex_linear.py

* Correct attribute names and also include primitive

* pass op_name when offloading calculation

Co-authored-by: AD1024 <dh63@cs.washington.edu>
Co-authored-by: Steven S. Lyubomirsky <sslyu@cs.washington.edu>
Co-authored-by: Bo-Yuan Huang <Bo-Yuan-Huang@users.noreply.github.com>

…1d-codegen

* Don't use checked_type for annotating types in the matcher (breaks tests and relies on type checking)

* Add callback feature to exact matcher, expand tests, simplify recent additions

…3la-pldi-push-main