github/SHARK-Studio
1
1
Fork 0
mirror of https://github.com/nod-ai/SHARK-Studio.git synced 2026-01-10 06:17:55 -05:00
Code Issues Packages Projects Releases Wiki Activity
1,749 Commits 66 Branches 705 Tags
6d80b43b6b281b3d2ace22d8ee83b2a64925cdae
Commit Graph

227 Commits

Author SHA1 Message Date
pdhirajkumarprasad
6d80b43b6b Migration to AMDShark 
Signed-off-by: pdhirajkumarprasad <dhirajp@amd.com>
 2025-11-20 12:46:36 +05:30
Marius Brehler
8c923e5eea Pin, update and replace action (#2180) 
* Pin and update actions
  Pins actions to tagged versions by its hashes as suggested by
  the OpenSSF Scorecard project.
* Replace the unmaintained `create-release` action
 2025-03-21 16:45:15 +01:00
Ean Garvey
d2c3752dc7 Fix batch count and tweaks to chatbot. (#2151) 
* Fix batch count

* Add button to unload models manually.

* Add compiled pipeline option

* Add brevitas to requirements

* Tweaks to chatbot

* Change script loading trigger
 2024-05-31 18:48:28 +05:30
Ean Garvey
68e9281778 (Studio2) Refactors SD pipeline to rely on turbine-models pipeline, fixes to LLM, gitignore (#2129) 
* Shark Studio SDXL support, HIP driver support, simpler device info, small fixes

* Fixups to llm API/UI and ignore user config files.

* Small fixes for unifying pipelines.

* Update requirements.txt for iree-turbine (#2130)

* Fix Llama2 on CPU (#2133)

* Filesystem cleanup and custom model fixes (#2127)

* Fix some formatting issues

* Remove IREE pin (fixes exe issue) (#2126)

* Update find links for IREE packages (#2136)

* Shark Studio SDXL support, HIP driver support, simpler device info, small fixes

* Abstract out SD pipelines from Studio Webui (WIP)

* Switch from pin to minimum torch version and fix index url

* Fix device parsing.

* Fix linux setup

* Fix custom weights.

---------

Co-authored-by: saienduri <77521230+saienduri@users.noreply.github.com>
Co-authored-by: gpetters-amd <159576198+gpetters-amd@users.noreply.github.com>
Co-authored-by: gpetters94 <gpetters@protonmail.com>
 2024-05-28 13:18:31 -04:00
gpetters94
6cb86a843e Remove IREE pin (fixes exe issue) (#2126) 
* Diagnose a build issue

* Remove IREE pin

* Revert the build on pull request change
 2024-04-30 12:27:30 -05:00
powderluv
a6a9e524c1 Drop linux nightly for now 2024-04-05 12:04:36 -07:00
powderluv
732df2e263 Updated signtool key 2024-04-05 12:01:42 -07:00
gpetters-amd
1ee16bd256 Fix the nightly build (#2111) 2024-04-05 19:22:33 +05:30
gpetters-amd
752d775fbd Fix a typo in the nightly build script (#2110) 2024-03-30 17:31:51 -07:00
gpetters-amd
4d1a6a204d Fix builder issue (#2109) 2024-03-30 16:21:55 -07:00
Daniel Garvey
ebfcfec338 remove shark 1.0 tests, add support for 2.0 llm 
* add support for external weights

* add tests and edit deps
 2023-12-14 21:44:37 -06:00
Ean Garvey
795fc33001 Update default compilation flags for data tiling. (#2000) 
* Update default CPU compilation flags.

c5a6cdc8dd

52eb7e9b82

tweak CPU iree-compile flags to match upstream changes.

* Add an option for data tiling on SD models.
 2023-11-30 17:05:37 -06:00
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
905d0103ff Revert "Re-enable SD tunings without matmuls. (#1976)" (#1979) 
This reverts commit 70817bb50a.
 2023-11-17 23:44:33 +05:30
Ean Garvey
4797bb89f5 Stringify path for ireec.compile_file (#1901) 
* Stringify path for ireec.compile_file

* Update test-models.yml
 2023-10-18 14:59:23 -05:00
powderluv
6da391c9b1 update signtool to use /fd certHash 2023-08-15 15:11:40 -07:00
Ean Garvey
343dfd901c Update SHARK-Runtime links to SRT (#1765) 
* Update nightly.yml

* Update setup_venv.ps1

* Update CMakeLists.txt

* Update shark_iree_profiling.md

* Update setup_venv.sh

* Update README.md

* Update .gitmodules

* Update CMakeLists.txt

* Update README.md

* fix signtool flags

* Update nightly.yml

* Update benchmark_utils.py

* uncomment tkinter launch
 2023-08-15 12:40:44 -07:00
Daniel Garvey
453e46562f mega vicuna merge pt 2 (#1685) 2023-07-24 12:42:20 -05:00
powderluv
3a24cff901 change binary names 2023-07-06 23:59:14 -07:00
powderluv
b9b8955f74 exclude vulkan on macos 2023-06-21 22:22:27 -07:00
powderluv
6f7a85eee3 switch to metal backend for CI 2023-06-21 22:17:11 -07:00
powderluv
fb865f1b99 Move to checkout@v3 
This will break Windows again but we have to fix it up since the old node.js is now deprecated.
 2023-06-19 18:44:36 -07:00
powderluv
7eaee9c242 update SHARK to nodai SHARK 2023-06-05 00:44:49 -07:00
powderluv
8230eebce5 Switch to CPU torch builds for shark.whl 2023-06-05 00:36:03 -07:00
powderluv
a2467e8d43 Enable SHARK whl packages 2023-06-04 23:21:22 -07:00
Ean Garvey
6c14847d1f xfail some large tests on macOS builder and switch to hash updates. (#1341) 
* Update test-models.yml

* Disable large tests on macOS builder
 2023-05-04 19:47:03 -05:00
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
Ean Garvey
96b1560da5 Make batch size configurable via pytest and fix sharktank generation. (#1227) 
* Fix sharktank generation and add batch_size pytest option for torch.

* Disable torch dynamo until py3.11 supported

* Compile torchmodel without dynamo if torch.compile fails

* Use release versions of TF/Keras for importer.

* Pin torchvision and remove debug prints.

* Remove duplicates from torch model list.

* Update generate_sharktank.py

* xfail a few models that fail sharktank generation/ numerics
 2023-03-28 14:33:39 -05:00
Daniel Garvey
5bb7846227 single entry point exe for all cli apps (#1158) 
usage:
add --app="img2img" (or "inpaint" "outpaint" "txt2img")
 2023-03-28 11:15:21 -05:00
Boian Petkantchin
783538fe11 Move linting opts from github workflow to config files 
This helps development where you can be sure that running locally

black .
flake8 .

will do the same as in the github job.
 2023-03-09 10:46:30 -08:00
Ean Garvey
116b128802 Use nightly shark_tank for test-models (#1133) 
* Use nightly shark_tank for test-models

* Update all_models.csv
 2023-03-02 12:33:36 -06:00
Daniel Garvey
23f1468cc6 disable most models on windows pytest (#1125) 2023-03-02 01:37:50 -06:00
Daniel Garvey
b1113ab551 disable benchmark on windows for pytest (#1100) 2023-02-28 18:10:29 -06:00
powderluv
abab59c25f Update nightly.yml 2023-02-22 18:44:43 -08:00
powderluv
c25840b585 Update nightly.yml 2023-02-22 18:34:37 -08:00
powderluv
1b3f9125bb Update nightly.yml 2023-02-22 18:23:44 -08:00
powderluv
b5d9f5ba49 Update nightly.yml 2023-02-22 18:20:31 -08:00
powderluv
e912c42bf0 update the openxla links 2023-02-22 12:10:23 -08:00
powderluv
e6841acf36 Publish nightlies as pre-releases 
So stable versions can be marked on the Releases page
 2023-02-22 12:05:28 -08:00
Daniel Garvey
681332ef32 fix tests after default flag changes (#1009) 
* fix tests after default flag changes

also adds support for import-mlir

* Update setup_venv.ps1

---------
 2023-02-16 12:57:50 -06:00
powderluv
13a255afad Update nightly.yml 2023-02-15 17:11:38 -08:00
Abhishek Varma
c203b65bf1 Fix __file__ AttributeError + Remove --enable_stack_trace (#1015) 2023-02-14 07:55:02 -08:00
powderluv
899cb9cc1f Temporarily disable signing of exe 2023-02-12 20:37:42 -08:00
powderluv
ef7d31293d Update tests to 3.11 2023-02-11 15:38:27 -08:00
powderluv
30eb10c990 Update to 3.11 2023-02-11 03:47:14 -08:00
Ean Garvey
c28cc4c919 Fix local_tank_cache handling in shark_downloader. (#981) 2023-02-09 14:52:03 -06:00
Ean Garvey
51300d33a7 Remove non-SD args from generate_sharktank.py (#970) 2023-02-07 13:29:55 -06:00
Ean Garvey
1eb9436836 Fix generate_sharktank args. 2023-02-07 14:06:07 +05:30
Ean Garvey
9604d9ce81 make --update_tank update only if hash mismatch 2023-02-07 14:06:07 +05:30
Ean Garvey
481d0553d8 Remove unnecessary repro_dir / shark_tmp usage 2023-02-07 14:06:07 +05:30