github/AMD-SHARK-Studio
1
1
Fork 0
mirror of https://github.com/nod-ai/AMD-SHARK-Studio.git synced 2026-04-03 03:00:17 -04:00
Code Issues Packages Projects Releases Wiki Activity
1,745 Commits 66 Branches 705 Tags
debug
Commit Graph

57 Commits

Author SHA1 Message Date
gpetters-amd
7db1612a5c Filesystem cleanup and custom model fixes (#2127) 
* Initial filesystem cleanup

* More filesystem cleanup

* Fix some formatting issues

* Address comments
 2024-04-30 11:18:33 -05:00
Ean Garvey
da50a16242 Create specified dir if needed during save_mlir and fix vulkan device fetching without URI/ID (#1989) 2023-11-23 01:01:41 -06:00
Ean Garvey
d051c3a4a7 Use clean_device_info() by default and don't write .mlir to /tmp/ (#1984) 
* Move clean_device_info to compile_utils

* Update compile_utils.py

* Fix .mlir writes for some user-level permissions

* Fix cases where full URI is given

* Fix conditionals.

* Fix device path handling in vulkan utils.
 2023-11-20 13:10:31 -06:00
Vivek Khandelwal
b83d32fafe Fix Falcon GPTQ Pipeline 2023-10-11 20:09:32 +05:30
Vivek Khandelwal
0a618e1863 Add support for Falcon GPTQ 2023-10-11 10:47:48 +05:30
Ean Garvey
caf6cc5d8f Switch most compile flows to use ireec.compile_file. (#1863) 
* Switch most compile flows to use ireec.compile_file.

* re-add input type to compile_str path.

* Check if mlir_module exists before checking if it's a path or pyobject.

* Fix some save_dir cases
 2023-10-06 23:04:43 -05:00
Vivek Khandelwal
8dd7850c69 Add Falcon-GPTQ support 2023-10-02 16:39:57 +05:30
Vivek Khandelwal
9681d494eb Update decomp list and shark trainer for DLRM 2023-09-06 21:24:50 +05:30
Abhishek Varma
87ae14b6ff [SD] Add sdpfa decomposition + update IREE flag 
-- This commit adds Scaled Dot Product Flash Attention's decomposition
   in shark_importer.
-- It also updates `iree-flow-enable-data-tiling` to `iree-opt-data-tiling`.

Signed-off-by: Abhishek Varma <abhishek@nod-labs.com>
 2023-09-04 18:03:53 +05:30
Ean Garvey
9c8cbaf498 Add support for ROCM (Windows) in Studio + compile utils (#1770) 
* WIP: MSVC ROCM support for SHARK Studio

* Make get_iree_rocm_args platform-agnostic.

* Update stable_args.py

* Update rocm arg handling in SD utils

* Guard quantization imports.

Co-authored-by: jam https://github.com/jammm
 2023-08-25 20:56:05 -07:00
jinchen62
8738571d1e Adapt the change of brevitas custom op name (#1772) 2023-08-17 14:24:43 -07:00
jinchen62
4d5c55dd9f Fix vicuna script (#1697) 2023-07-27 17:24:26 -05:00
jinchen62
bc6fee1a0c Add int4/int8 vicuna (#1598) 2023-07-05 07:01:51 -07:00
Prashant Kumar
a811b867b9 Add shark_eager mode. 
-- Eager mode with step by step op compilation and execution.
 2023-06-22 22:59:14 +05:30
Vivek Khandelwal
015d0132c3 Modify falcon pipeline to add fp16 support (#1551) 2023-06-19 09:57:13 -07:00
Chi_Liu
f60ab1f4fa Add Deberta to stablehlo in shark tank (#1545) 2023-06-16 13:24:44 -07:00
dan
bec82a665f mega vicuna merge 
single endpoint in apps/language/models/scripts/vicuna.py
removed main functions from pipelines
replaced divergent utils compile with shark_importer
adds support for different precisions
 2023-06-14 19:06:29 +05:30
Ean Garvey
44273b0791 Fix conditional in transform_fx() (#1530) 2023-06-13 16:24:53 -05:00
Prashant Kumar
0a4c8fcb3e Minor changes in the fx transforms. 2023-06-13 21:23:35 +05:30
Stefan Kapusniak
2fec3c8169 re-indents add_upcast in shark importer (#1523) 
* The two with blocks in add_upcast appear to be underindented making
SD 1.4 break on rdna3, I've pushed them out one more tab, and then
everything appears to work again.
 2023-06-12 14:41:10 -05:00
Prashant Kumar
b6dbd20250 Modify the fx transforms. (#1521) 
- The bounds are set properly.
- The upcasting and downcasting is done for vicuna.
 2023-06-12 09:40:14 -07:00
Prashant Kumar
8e571d165f Enable cpu f16 dtype tracing for the vicuna model. (#1461) 2023-05-24 09:37:57 -07:00
Chi_Liu
64c2b2d96b Add gpt2 to stablehlo support in shark tank (#1447) 
- Add torch decomposition support when generating shark tank
- Add gpt2 stablehlo
 2023-05-22 10:45:51 -07:00
Chi_Liu
a0097a1ead Add mlir_type for torch_model_list.csv (#1428) 
- Enable stablehlo/tosa mlir output for torch model
- Add BERT stablehlo support
 2023-05-15 10:23:54 -07:00
Chi_Liu
aa8ada9da9 Add support for torch to stablehlo and tosa in shark_importer (#1360) 2023-04-27 08:09:45 -07:00
Ean Garvey
2191fc8952 Separate pytest benchmark modes and fix model updates for SHARK downloader / pytest. (#1264) 
* Only xfail windows models in CI

* downloader: make model updates more robust.

* Separate baseline and native benchmarks in pytest.

* Fix native benchmarks

* Fix torchvision model utils.
 2023-04-03 08:24:21 -07:00
gpetters94
7899e1803a Add fix for attention slicing fp16 (#1217) 2023-03-20 19:11:29 -07:00
Daniel Garvey
62b5a9fd49 generate sharktank for apps dir (#966) 
* merge confix resolution

* add support to other scripts

---------

Co-authored-by: dan <dan@nod-labs.com>
 2023-03-13 10:54:15 -07:00
Ean Garvey
481d0553d8 Remove unnecessary repro_dir / shark_tmp usage 2023-02-07 14:06:07 +05:30
Ean Garvey
a504903dd5 Fix formatting issues. (#903) 2023-02-01 09:12:45 +05:30
Daniel Garvey
a4634632ba add generate_sharktank for stable_diffusion model defaults (#742) 
Co-authored-by: dan <dan@nod-labs.com>
Co-authored-by: powderluv <powderluv@users.noreply.github.com>
 2023-01-31 09:44:54 -08:00
yzhang93
fee73b0b63 Add SD model annotation on fly (#869) 
* Add SD model annotation on fly

* Move tuned_compile_through_fx to utils

* Fix SD compilation flags
 2023-01-26 11:46:36 -08:00
stanley
c4a9365aa1 [Shark][Training] Refresh SharkTrainer to latest APIs. 2023-01-19 20:30:15 +00:00
Prashant Kumar
5a1fc6675a This PR adds --import-mlir for f16 tensors without cuda. 2023-01-13 22:19:53 +05:30
Prashant Kumar
6f80825814 Modify import_with_fx to import with dtype=f16. 2023-01-13 22:19:53 +05:30
Prashant Kumar
4cb50a3d06 Update the models to 8th Dec version. 2022-12-14 00:01:46 +05:30
Prashant Kumar
7b1f04d121 Changes incorporating the recent torch_mlir compile api changes. 2022-11-15 15:25:37 +05:30
Phaneesh Barwaria
749a2c2dec add support for choosing vulkan device (#439) 2022-11-12 14:00:41 -08:00
Ean Garvey
fd7baae548 Serialize torch-mlir CAPI module as bytecode instead of string. (#435) 
* Serialize torch-mlir CAPI as bytecode instead of string.

* Minor fixes to MLIR data handling in SHARK python.
 2022-10-27 14:37:15 -05:00
Ean Garvey
9956099516 Add pytest option for updating tank and fix save_mlir function. (#413) 
* Use IREE tf tools to save .mlir modules when generating shark_tank.

* Add option to pytest for enabling auto-updates to local shark tank.

* xfail mobilenet torch on cpu, cuda and fix CI macos setup

* Update test-models.yml to disable macos vulkan CI.
 2022-10-25 21:29:18 +05:30
Prashant Kumar
38ae6b5af4 Add stable_diffusion fp16 and fp32 with args. 2022-10-20 21:47:11 +05:30
Ean Garvey
0bfe30d75d Fix issues with extra_args in benchmarks, pin tf==2.10 (#411) 2022-10-20 06:55:26 -07:00
Ean Garvey
a3654f33da Fix sourcing for canonical MiniLM shark_tank model artifacts. (#278) 
* Fix generation of MiniLM artifacts.

* Fix miniLM output for validation. Xfail numerics failure on mpnet.

* Update distilbert-base-uncased_tf_test.py

* try-except for transition of minilm model
 2022-08-17 23:03:47 -05:00
Chi_Liu
af4257d05f Add tf image classification auto model (#213) 2022-07-26 23:18:42 -07:00
Chi_Liu
dc1a283ab7 Remove tf package dep for SharkDownloader tflite tests (#212) 2022-07-26 12:41:12 -07:00
Prashant Kumar
49fc6d2f4b Add all the tf models to gs::shark_tank. (#207) 
-- Tensorflow models have been imported to shark_tank.
-- TF Tests have been updated to use the downloader.
 2022-07-22 11:53:07 -05:00
Prashant Kumar
3c2f8ef243 Generate shark_tank for tensorflow models. 
Updated the generate_sharktank.py script to give tensorflow models.
 2022-07-20 22:37:14 +05:30
Prashant Kumar
0dcf387089 Add shark_importer for torch_models. (#183) 
All the torch_models are imported to gs::shark_tank.
Scripts have been updated.
 2022-07-12 20:38:19 -07:00
Anush Elangovan
a7435973d9 Fix black formatting 2022-06-30 20:42:02 +00:00
Chi_Liu
2adea76b8c Enable SharkImporter Tests (#165) 
rewrite some tflite code from SharkImporter to tflite_utils.py
 2022-06-29 10:11:48 -07:00