torch-mlir/docs
Ramiro Leal-Cavazos de02b56e17
Replace RefineTypes with dtype functions (#2105)
This commit adds dtype functions for all the torch ops that did not
previously have one and removes the pass `RefineTypes`, since the
abstract interpretation library now takes care of all the dtype
propagation.

All dtype functions added are tested except for
- `aten.embedding`
- `aten._embedding_bag`
- `aten.embedding_bag`

These functions need a change to the testing framework to allow
specifying the actual data inside the tensor used for testing. I will
fix this in a follow up patch.

Co-authored-by: Jiahao Li <liplus17@163.com>
2023-05-12 13:40:45 -07:00
..
images [docs] Centralize all images in docs/images/ 2022-11-04 03:12:17 -07:00
abstract_interp_lib.md [custom op] Generalize shape library logic to work with dtypes (#1594) 2022-12-13 08:25:41 -08:00
adding_abstract_interpretation_functions.md Change dtype functions interface to take ints tuple for each tensor (#1965) 2023-03-23 11:05:39 -07:00
adding_an_e2e_test.md [docs] Add info about special e2e testing cases. 2022-12-07 12:53:07 +01:00
architecture.md Replace RefineTypes with dtype functions (#2105) 2023-05-12 13:40:45 -07:00
code_owners.md mhlo: migrate conversion to stablehlo (#1840) 2023-02-02 07:29:47 -06:00
development.md mhlo: migrate conversion to stablehlo (#1840) 2023-02-02 07:29:47 -06:00
long_term_roadmap.md Update long_term_roadmap.md 2023-03-27 12:34:07 -07:00
ltc_backend.md [docs] Centralize all images in docs/images/ 2022-11-04 03:12:17 -07:00
ltc_examples.md Fix LTC lib_torch_mlir_ltc.so import error (#1283) 2022-08-25 18:25:01 -04:00